To see the other types of publications on this topic, follow the link: Variational Autoencoders (VAEs).
Journal articles on the topic 'Variational Autoencoders (VAEs)'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Variational Autoencoders (VAEs).'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Singh, Aman, and Tokunbo Ogunfunmi. "An Overview of Variational Autoencoders for Source Separation, Finance, and Bio-Signal Applications." Entropy 24, no. 1 (2021): 55. http://dx.doi.org/10.3390/e24010055.
Full textAbstract:
Autoencoders are a self-supervised learning system where, during training, the output is an approximation of the input. Typically, autoencoders have three parts: Encoder (which produces a compressed latent space representation of the input data), the Latent Space (which retains the knowledge in the input data with reduced dimensionality but preserves maximum information) and the Decoder (which reconstructs the input data from the compressed latent space). Autoencoders have found wide applications in dimensionality reduction, object detection, image classification, and image denoising applications. Variational Autoencoders (VAEs) can be regarded as enhanced Autoencoders where a Bayesian approach is used to learn the probability distribution of the input data. VAEs have found wide applications in generating data for speech, images, and text. In this paper, we present a general comprehensive overview of variational autoencoders. We discuss problems with the VAEs and present several variants of the VAEs that attempt to provide solutions to the problems. We present applications of variational autoencoders for finance (a new and emerging field of application), speech/audio source separation, and biosignal applications. Experimental results are presented for an example of speech source separation to illustrate the powerful application of variants of VAE: VAE, β-VAE, and ITL-AE. We conclude the paper with a summary, and we identify possible areas of research in improving performance of VAEs in particular and deep generative models in general, of which VAEs and generative adversarial networks (GANs) are examples.
2
Lyu, Zhuoyue, Safinah Ali, and Cynthia Breazeal. "Introducing Variational Autoencoders to High School Students." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (2022): 12801–9. http://dx.doi.org/10.1609/aaai.v36i11.21559.
Full textAbstract:
Generative Artificial Intelligence (AI) models are a compelling way to introduce K-12 students to AI education using an artistic medium, and hence have drawn attention from K-12 AI educators. Previous Creative AI curricula mainly focus on Generative Adversarial Networks (GANs) while paying less attention to Autoregressive Models, Variational Autoencoders (VAEs), or other generative models, which have since become common in the field of generative AI. VAEs' latent-space structure and interpolation ability could effectively ground the interdisciplinary learning of AI, creative arts, and philosophy. Thus, we designed a lesson to teach high school students about VAEs. We developed a web-based game and used Plato's cave, a philosophical metaphor, to introduce how VAEs work. We used a Google Colab notebook for students to re-train VAEs with their hand-written digits to consolidate their understandings. Finally, we guided the exploration of creative VAE tools such as SketchRNN and MusicVAE to draw the connection between what they learned and real-world applications. This paper describes the lesson design and shares insights from the pilot studies with 22 students. We found that our approach was effective in teaching students about a novel AI concept.
3
Nugroho, Herminarto, Meredita Susanty, Ade Irawan, Muhamad Koyimatu, and Ariana Yunita. "Fully Convolutional Variational Autoencoder For Feature Extraction Of Fire Detection System." Jurnal Ilmu Komputer dan Informasi 13, no. 1 (2020): 9. http://dx.doi.org/10.21609/jiki.v13i1.761.
Full textAbstract:
This paper proposes a fully convolutional variational autoencoder (VAE) for features extraction from a large-scale dataset of fire images. The dataset will be used to train the deep learning algorithm to detect fire and smoke. The features extraction is used to tackle the curse of dimensionality, which is the common issue in training deep learning with huge datasets. Features extraction aims to reduce the dimension of the dataset significantly without losing too much essential information. Variational autoencoders (VAEs) are powerfull generative model, which can be used for dimension reduction. VAEs work better than any other methods available for this purpose because they can explore variations on the data in a specific direction.
4
Papadopoulos, Dimitris, and Vangelis D. Karalis. "Variational Autoencoders for Data Augmentation in Clinical Studies." Applied Sciences 13, no. 15 (2023): 8793. http://dx.doi.org/10.3390/app13158793.
Full textAbstract:
Sample size estimation is critical in clinical trials. A sample of adequate size can provide insights into a given population, but the collection of substantial amounts of data is costly and time-intensive. The aim of this study was to introduce a novel data augmentation approach in the field of clinical trials by employing variational autoencoders (VAEs). Several forms of VAEs were developed and used for the generation of virtual subjects. Various types of VAEs were explored and employed in the production of virtual individuals, and several different scenarios were investigated. The VAE-generated data exhibited similar performance to the original data, even in cases where a small proportion of them (e.g., 30–40%) was used for the reconstruction of the generated data. Additionally, the generated data showed even higher statistical power than the original data in cases of high variability. This represents an additional advantage for the use of VAEs in situations of high variability, as they can act as noise reduction. The application of VAEs in clinical trials can be a useful tool for decreasing the required sample size and, consequently, reducing the costs and time involved. Furthermore, it aligns with ethical concerns surrounding human participation in trials.
5
Kiran, Vadduri Uday. "HAVAE – An Advanced Approach for Malware Detection Using Deep Learning." International Journal for Research in Applied Science and Engineering Technology 12, no. 3 (2024): 2740–46. http://dx.doi.org/10.22214/ijraset.2024.59303.
Full textAbstract:
Abstract: The dynamic situation of cybersecurity necessitates continuous adaptation to the evolving and sophisticated nature of malware. This study proposes an innovative approach to enhancing threat detection methodologies by combining Adversarial Autoencoders (AAEs) and Variational Autoencoders (VAEs) for unsupervised malware detection. AAEs, with their EncoderDecoder structure and adversarial techniques, are integrated with VAEs to discern latent representations which are crucial for discriminating between malware and harmless software. This model, referred to as Hybrid Adversarial-Variational Autoencoder (HAVAE), takes advantage of both of their strengths architectures, capturing nuanced features within a latent space through unsupervised learning. The HAVAE model employs the Reparameterization Technique, crucial for sampling latent variables, ensuring the generation of realistic samples while retaining discriminative attributes essential for accurate malware identification. Through comprehensive evaluations across diverse datasets, the efficiency of HAVAE is assessed using metrics encompassing precision, recall, and F1-score. The evaluation underscores the model's robust ability to detect malicious software effectively, emphasizing its potential as a versatile cybersecurity tool. This innovative approach represents a revolution in cybersecurity, utilizing the strength of unsupervised learning techniques, AAEs, and VAEs. The findings signify a significant advancement in adaptive and resilient malware detection systems, illuminating pathways for improved threat identification and mitigation in the ever-evolving cybersecurity landscape
6
Battey, C. J., Gabrielle C. Coffing, and Andrew D. Kern. "Visualizing population structure with variational autoencoders." G3 Genes|Genomes|Genetics 11, no. 1 (2021): 1–11. http://dx.doi.org/10.1093/g3journal/jkaa036.
Full textAbstract:
Abstract Dimensionality reduction is a common tool for visualization and inference of population structure from genotypes, but popular methods either return too many dimensions for easy plotting (PCA) or fail to preserve global geometry (t-SNE and UMAP). Here we explore the utility of variational autoencoders (VAEs)—generative machine learning models in which a pair of neural networks seek to first compress and then recreate the input data—for visualizing population genetic variation. VAEs incorporate nonlinear relationships, allow users to define the dimensionality of the latent space, and in our tests preserve global geometry better than t-SNE and UMAP. Our implementation, which we call popvae, is available as a command-line python program at github.com/kr-colab/popvae. The approach yields latent embeddings that capture subtle aspects of population structure in humans and Anopheles mosquitoes, and can generate artificial genotypes characteristic of a given sample or population.
7
Potu, Rakshitha Reddy, Naalla Sushma, Baru Shiva Kumar, and Aruna Kumari Kumbhagiri. "Real Image Restoration Using VAEs." International Journal for Research in Applied Science and Engineering Technology 10, no. 6 (2022): 889–98. http://dx.doi.org/10.22214/ijraset.2022.43964.
Full textAbstract:
Abstract— Old photos are an integral part of everybody’s life; they remind us of how one person has spent their life. As people used hard copies of photos before, those photos suffered severe degradation. This degradation in real-time images is intricate, causing thetypical restoration that might be solved through supervised learning to fail to generalize due to the domain gap between synthetic and real images. Therefore, this method uses various autoencoders to restore and colourize old images. Furthermore, this model uses a unique triplet domain translation network on real images and synthetic photo pairs. Precisely, VAEs, which are variational autoencoders, are trained to transform old pictures and clean pictures into two latent spaces. Therefore, the translation between these two latent spaces is comprehended with simulated paired data. This translation generalizes well to authentic images because the domain gap is encompassed in the close-packed latent space. Moreover, to manoeuvre numerous degradations present in one old picture, this model designs aworld branchwith a partial non-local block targeting the structured faults, like scrapes and dirt marks, and an area branch targeting unstructured faults, like noisesand fuzziness. Two branches are blended within the latent space, resulting in an improved ability to renew old pictures from numerous defects. Additionally, it applies another face refinementnetwork to revive fine details of faces within the old pictures, thus generating photos with amplified quality. Another autoencoder is encoded with colour images, and then the decoder decodes the features extracted from the encoder. Once a model is trained, testing is performed to colourize the photographs. Keywords— Degraded pictures, Variational Auto Encoders, Domain gap, Triplet domaintranslation.
8
Yang, FengLei, Fei Liu, and ShanShan Liu. "Collaborative Filtering Based on a Variational Gaussian Mixture Model." Future Internet 13, no. 2 (2021): 37. http://dx.doi.org/10.3390/fi13020037.
Full textAbstract:
Collaborative filtering (CF) is a widely used method in recommendation systems. Linear models are still the mainstream of collaborative filtering research methods, but non-linear probabilistic models are beyond the limit of linear model capacity. For example, variational autoencoders (VAEs) have been extensively used in CF, and have achieved excellent results. Aiming at the problem of the prior distribution for the latent codes of VAEs in traditional CF is too simple, which makes the implicit variable representations of users and items too poor. This paper proposes a variational autoencoder that uses a Gaussian mixture model for latent factors distribution for CF, GVAE-CF. On this basis, an optimization function suitable for GVAE-CF is proposed. In our experimental evaluation, we show that the recommendation performance of GVAE-CF outperforms the previously proposed VAE-based models on several popular benchmark datasets in terms of recall and normalized discounted cumulative gain (NDCG), thus proving the effectiveness of the algorithm.
9
Akkari, Nissrine, Fabien Casenave, Elie Hachem, and David Ryckelynck. "A Bayesian Nonlinear Reduced Order Modeling Using Variational AutoEncoders." Fluids 7, no. 10 (2022): 334. http://dx.doi.org/10.3390/fluids7100334.
Full textAbstract:
This paper presents a new nonlinear projection based model reduction using convolutional Variational AutoEncoders (VAEs). This framework is applied on transient incompressible flows. The accuracy is obtained thanks to the expression of the velocity and pressure fields in a nonlinear manifold maximising the likelihood on pre-computed data in the offline stage. A confidence interval is obtained for each time instant thanks to the definition of the reduced dynamic coefficients as independent random variables for which the posterior probability given the offline data is known. The parameters of the nonlinear manifold are optimized as the ones of the decoder layers of an autoencoder. The parameters of the conditional posterior probability of the reduced coefficients are the ones of the encoder layers of the same autoencoder. The optimization of both sets of the encoder and the decoder parameters is obtained thanks to the application of a variational Bayesian method, leading to variational autoencoders. This Reduced Order Model (ROM) is not a regression model over the offline pre-computed data. The numerical resolution of the ROM is based on the Chorin projection method. We apply this new nonlinear projection-based Reduced Order Modeling (ROM) for a 2D Karman Vortex street flow and a 3D incompressible and unsteady flow in an aeronautical injection system.
10
Wang, Ziyang. "Addressing Posterior Collapse in Variational Autoencoders with β-VAE". Highlights in Science, Engineering and Technology 57 (11 липня 2023): 161–67. http://dx.doi.org/10.54097/hset.v57i.9995.
Full textAbstract:
Posterior collapse is a pervasive issue in Variational Autoencoders (VAEs) that leads to the learned latent representations becoming trivial and devoid of meaningful information. To address this problem, this paper presents a novel β-VAE approach, which incorporates a hyperparameter β to strike an optimal balance between the reconstruction loss and the KL divergence loss. By conducting a comprehensive series of experiments and drawing comparisons with existing methods, robust evidence is provided that the proposed β-VAE method effectively mitigates posterior collapse and yields more expressive and informative latent representations.The experimental setup involves various architectures and datasets to demonstrate the versatility and efficacy of the β-VAE approach in diverse settings. Additionally, ablation studies are performed to investigate the impact of different β values on the model's performance, elucidating the role of this hyperparameter in controlling the trade-off between reconstruction quality and latent representation expressiveness. Furthermore, the disentanglement properties of the learned latent space are analyzed, which is a crucial aspect of VAEs, especially when applied to complex, real-world data.In-depth analysis of the results offers valuable insights into the underlying mechanisms of β-VAE, thereby contributing to a more profound understanding of VAEs and their inherent limitations. The findings not only establish the effectiveness of the β-VAE method in preventing posterior collapse but also pave the way for future research on improving VAEs' performance in various applications. Potential future work could explore alternative techniques for balancing the competing objectives of reconstruction and latent representation learning or delve into the theoretical properties of β-VAE, providing a more rigorous foundation for this approach.
11
Liu, Jianing. "Research on the Application of Variational Autoencoder in Image Generation." ITM Web of Conferences 70 (2025): 02001. https://doi.org/10.1051/itmconf/20257002001.
Full textAbstract:
The rapid development of artificial intelligence and deep learning has significantly influenced the domain of image creation, finding extensive applications in applications in fields like medical imaging, computer vision, and entertainment. Despite these advancements, challenges remain, especially in enhancing the quality and variety of produced images. This paper concentrates on applying Variational Autoencoders (VAEs) to image generation, a topic of increasing importance due to the model’s theoretical interpretability and stability. Through a detailed analysis of VAE principles, architecture, and applications, this research underscores the model’s capabilities in producing high-quality, varied images and its effectiveness in tasks such as image denoising and enhancement. The study also analysis the limitations of VAEs, like the inclination to generate blurry images, and discusses potential improvements, including hybrid models and enhanced loss functions. The results of this research enhance the comprehension of VAE’s capabilities and provide a foundation for future research aimed at advancing image generation technologies.
12
Agarwal, Aman. "Application of Music Retrieval & Generation." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem34003.
Full textAbstract:
The research explores music generation through LSTM and VAEs neural network architectures, leveraging MIDI representations. LSTM specializes in sequential data processing, while VAEs compress music datasets into low-dimensional representations. Optimization of models is pursued by analyzing the relationship between training loss and epochs. Ultimately, a comparison between LSTM and VAEs determines the most effective algorithm for music generation. Traditional methods face issues like vanishing and exploding gradients, prompting exploration of deep learning approaches. The study aims to advance machine manipulation of music, facilitating new composition generation from existing MIDI files. Keywords: Music generation, LSTM, Variational Autoencoders (VAEs), MIDI representation, Sequential data, Neural network architectures, Training loss, Optimization, Deep learning, Vanishing gradient, Exploding gradient
13
Mohamed, Mahmoud. "Comparative Evaluation of VAEs, VAE-GANs and AAEs for Anomaly Detection in Network Intrusion Data." EMITTER International Journal of Engineering Technology 11, no. 2 (2023): 160–73. http://dx.doi.org/10.24003/emitter.v11i2.817.
Full textAbstract:
With cyberattacks growing in frequency and sophistication, effective anomaly detection is critical for securing networks and systems. This study provides a comparative evaluation of deep generative models for detecting anomalies in network intrusion data. The key objective is to determine the most accurate model architecture. Variational autoencoders (VAEs), VAE-GANs, and adversarial autoencoders (AAEs) are tested on the NSL-KDD dataset containing normal traffic and different attack types. Results show that AAEs significantly outperform VAEs and VAE-GANs, achieving AUC scores up to 0.96 and F1 scores of 0.76 on novel attacks. The adversarial regularization of AAEs enables superior generalization capabilities compared to standard VAEs. VAE-GANs exhibit better accuracy than VAEs, demonstrating the benefits of adversarial training. However, VAE-GANs have higher computational requirements. The findings provide strong evidence that AAEs are the most effective deep anomaly detection technique for intrusion detection systems. This study delivers novel insights into optimizing deep learning architectures for cyber defense. The comparative evaluation methodology and results will aid researchers and practitioners in selecting appropriate models for operational network security.
14
Sheng, Xin, Linli Xu, Junliang Guo, Jingchang Liu, Ruoyu Zhao, and Yinlong Xu. "IntroVNMT: An Introspective Model for Variational Neural Machine Translation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (2020): 8830–37. http://dx.doi.org/10.1609/aaai.v34i05.6411.
Full textAbstract:
We propose a novel introspective model for variational neural machine translation (IntroVNMT) in this paper, inspired by the recent successful application of introspective variational autoencoder (IntroVAE) in high quality image synthesis. Different from the vanilla variational NMT model, IntroVNMT is capable of improving itself introspectively by evaluating the quality of the generated target sentences according to the high-level latent variables of the real and generated target sentences. As a consequence of introspective training, the proposed model is able to discriminate between the generated and real sentences of the target language via the latent variables generated by the encoder of the model. In this way, IntroVNMT is able to generate more realistic target sentences in practice. In the meantime, IntroVNMT inherits the advantages of the variational autoencoders (VAEs), and the model training process is more stable than the generative adversarial network (GAN) based models. Experimental results on different translation tasks demonstrate that the proposed model can achieve significant improvements over the vanilla variational NMT model.
15
Wei, Ruoqi, and Ausif Mahmood. "Optimizing Few-Shot Learning Based on Variational Autoencoders." Entropy 23, no. 11 (2021): 1390. http://dx.doi.org/10.3390/e23111390.
Full textAbstract:
Despite the importance of few-shot learning, the lack of labeled training data in the real world makes it extremely challenging for existing machine learning methods because this limited dataset does not well represent the data variance. In this research, we suggest employing a generative approach using variational autoencoders (VAEs), which can be used specifically to optimize few-shot learning tasks by generating new samples with more intra-class variations on the Labeled Faces in the Wild (LFW) dataset. The purpose of our research is to increase the size of the training dataset using various methods to improve the accuracy and robustness of the few-shot face recognition. Specifically, we employ the VAE generator to increase the size of the training dataset, including the basic and the novel sets while utilizing transfer learning as the backend. Based on extensive experimental research, we analyze various data augmentation methods to observe how each method affects the accuracy of face recognition. The face generation method based on VAEs with perceptual loss can effectively improve the recognition accuracy rate to 96.47% using both the base and the novel sets.
16
Rivero, Daniel, Iván Ramírez-Morales, Enrique Fernandez-Blanco, Norberto Ezquerra, and Alejandro Pazos. "Classical Music Prediction and Composition by Means of Variational Autoencoders." Applied Sciences 10, no. 9 (2020): 3053. http://dx.doi.org/10.3390/app10093053.
Full textAbstract:
This paper proposes a new model for music prediction based on Variational Autoencoders (VAEs). In this work, VAEs are used in a novel way to address two different issues: music representation into the latent space, and using this representation to make predictions of the future note events of the musical piece. This approach was trained with different songs of Handel. As a result, the system can represent the music in the latent space, and make accurate predictions. Therefore, the system can be used to compose new music either from an existing piece or from a random starting point. An additional feature of this system is that a small dataset was used for training. However, results show that the system is able to return accurate representations and predictions on unseen data.
17
Basit, Jamshaid, Danish Hanif, and Madiha Arshad. "Quantum Variational Autoencoders for Predictive Analytics in High Frequency Trading Enhancing Market Anomaly Detection." International Journal of Emerging Multidisciplinaries: Computer Science & Artificial Intelligence 3, no. 1 (2024): 21. http://dx.doi.org/10.54938/ijemdcsai.2024.03.1.319.
Full textAbstract:
High-frequency trading (HFT) markets, characterized by high and frequent price fluctuations, necessitate the use of anomaly detection mechanisms to monitor the market and ensure the efficacy of the trading system. This paper aims to discuss the possibility of improving predictive analytics in HFT using quantum computing with the help of the Quantum Variational Autoencoder (QL-VAE). As a result, we propose a new direction for further research on quantum VAEs in HFT that involves their direct comparison with classical VAEs. The application of quantum models for mastering the intensive data flow of HFT is conditioned by the advantages of quantum computation in comparison to classical ones, which are more suitable for handling multidimensional data arrangements and intricate topologies. Our detailed study methodology involved examining various aspects of HFT data, such as order book features and stock price characteristics. We normalized all the data and reduced some of its dimensions. We established quantum VAEs using Pennylane, and configured the classical VAEs using TensorFlow. When it comes to market anomalies, the results of the comparative analysis showed higher accuracy, recall, and F1 rate in quantum VAEs compared to classical models when it comes to the analysis of market anomalies. Therefore, the quantum model's ability to handle high-dimensional data makes it a better fit for HFT than classical methods. These studies suggest that quantum VAEs could significantly improve anomaly detection in the financial market.
18
Kuang, Shenfen, Jie Song, Shangjiu Wang, and Huafeng Zhu. "Variational Autoencoding with Conditional Iterative Sampling for Missing Data Imputation." Mathematics 12, no. 20 (2024): 3288. http://dx.doi.org/10.3390/math12203288.
Full textAbstract:
Variational autoencoders (VAEs) are popular for their robust nonlinear representation capabilities and have recently achieved notable advancements in the problem of missing data imputation. However, existing imputation methods often exhibit instability due to the inherent randomness in the sampling process, leading to either underestimation or overfitting, particularly when handling complex missing data types such as images. To address this challenge, we introduce a conditional iterative sampling imputation method. Initially, we employ an importance-weighted beta variational autoencoder to learn the conditional distribution from the observed data. Subsequently, leveraging the importance-weighted resampling strategy, samples are drawn iteratively from the conditional distribution to compute the conditional expectation of the missing data. The proposed method has been experimentally evaluated using classical generative datasets and compared with various well-known imputation methods to validate its effectiveness.
19
Gonzalez, Adrian. "Artificial Intelligence as an Art Director." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 16, no. 1 (2020): 337–39. http://dx.doi.org/10.1609/aiide.v16i1.7454.
Full textAbstract:
My research focuses on the design of an artificial intelligence-based system that can perform the tasks of a videogame art director. I began with the analysis of game developers’ design processes, workflows, and methodologies. I observed they involve fast-paced proposal-evaluation-correction cycles. This, along with my interest in generative methods, led me to consider using Variational Autoencoders (VAEs), which also include similar cycles, and do not require a high number of samples to produce satisfactory results. Currently, I am using VAEs on experiments over Pokémon images, with positive results.
20
Narula, Anushka. "A Comparative Study of GANs and VAEs for Image Generation." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 02 (2025): 1–9. https://doi.org/10.55041/ijsrem41480.
Full textAbstract:
Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) are two of the most prominent generative models for image synthesis. This paper provides a comprehensive comparison of GANs and VAEs, focusing on their architectures, training methodologies, and performance in image generation tasks. We also evaluate their differences in terms of stability, quality, and diversity of outputs, supported by quantitative metrics such as Frechet Inception Distance (FID) and´ Inception Score (IS). A detailed analysis of their applications in various domains is presented, along with a discussion on their limitations and future directions.
21
Rosalina, Rosalina, and Genta Sahuri. "MIDI-based generative neural networks with variational autoencoders for innovative music creation." International Journal of Advances in Applied Sciences 13, no. 2 (2024): 360. http://dx.doi.org/10.11591/ijaas.v13.i2.pp360-370.
Full textAbstract:
By utilizing variational autoencoder (VAE) architectures in musical instrument digital interface (MIDI)-based generative neural networks (GNNs), this study explores the field of creative music composition. The study evaluates the success of VAEs in generating musical compositions that exhibit both structural integrity and a resemblance to authentic music. Despite achieving convergence in the latent space, the degree of convergence falls slightly short of initial expectations. This prompts an exploration of contributing factors, with a particular focus on the influence of training data variation. The study acknowledges the optimal performance of VAEs when exposed to diverse training data, emphasizing the importance of sufficient intermediate data between extreme ends. The intricacies of latent space dimensions also come under scrutiny, with challenges arising in creating a smaller latent space due to the complexities of representing data in N dimensions. The neural network tends to position data further apart, and incorporating additional information necessitates exponentially more data. Despite the suboptimal parameters employed in the creation and training process, the study concludes that they are sufficient to yield commendable results, showcasing the promising potential of MIDI-based GNNs with VAEs in pushing the boundaries of innovative music composition.
22
Rosalina and Sahuri Genta. "MIDI-based generative neural networks with variational autoencoders for innovative music creation." International Journal of Advances in Applied Sciences (IJAAS) 13, no. 2 (2024): 360–70. https://doi.org/10.11591/ijaas.v13.i2.pp360-370.
Full textAbstract:
By utilizing variational autoencoder (VAE) architectures in musical instrument digital interface (MIDI)-based generative neural networks (GNNs), this study explores the field of creative music composition. The study evaluates the success of VAEs in generating musical compositions that exhibit both structural integrity and a resemblance to authentic music. Despite achieving convergence in the latent space, the degree of convergence falls slightly short of initial expectations. This prompts an exploration of contributing factors, with a particular focus on the influence of training data variation. The study acknowledges the optimal performance of VAEs when exposed to diverse training data, emphasizing the importance of sufficient intermediate data between extreme ends. The intricacies of latent space dimensions also come under scrutiny, with challenges arising in creating a smaller latent space due to the complexities of representing data in N dimensions. The neural network tends to position data further apart, and incorporating additional information necessitates exponentially more data. Despite the suboptimal parameters employed in the creation and training process, the study concludes that they are sufficient to yield commendable results, showcasing the promising potential of MIDI-based GNNs with VAEs in pushing the boundaries of innovative music composition.
23
Shukla, Abhishek. "Innovative Ways of Utilizing Generative AI for Graphical Big Data Analysis." Journal of Artificial Intelligence & Cloud Computing 3, no. 1 (2024): 1–3. http://dx.doi.org/10.47363/jaicc/2024(3)222.
Full textAbstract:
This essay explores the integration of Generative Artificial Intelligence (AI) models, including Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), in graphical big data analysis. Generative AI offers the generation of synthetic graphical data, improves data visualizations, and aids in pattern recognition within complex datasets. It presents innovative solutions to the challenges posed by large and intricate graphical datasets, enhancing the depth and accuracy of data analysis.
24
Xenaki, Angeliki, Yan Pailhas, and Alessandro Monti. "Platform motion estimation in multiple-input multiple-output synthetic aperture sonar with coupled variational autoencoders." Journal of the Acoustical Society of America 154, no. 4_supplement (2023): A305. http://dx.doi.org/10.1121/10.0023610.
Full textAbstract:
Synthetic aperture sonar (SAS) utilizes the motion of the platform carrying the sonar system to synthesize an aperture that is much longer than thephysical antenna by coherently combining data from several pings. Coherent processing in SAS requires platform motion estimation and compensation with sub-wavelength accuracy for high-resolution imaging. Micronavigation, i.e., through-the-sensor platform motion estimation from spatio-temporal coherence measurements of diffuse backscatter on overlapping recordings between successive pings, is essential when positioning information from navigational instruments is absent or inadequately accurate. Representation learning with a variational autoencoder (VAE) offers an unsupervised data-driven micronavigation solution. In this study, we introduce a hierarchical variational model implemented with coupled VAEs to relate the common latent features between datasets of coherence measurements in broadband multiple-input multiple-output SAS systems. We show that self-supervising the training process of independently parameterized but coupled VAEs improves significantly the accuracy of the micronavigation estimates.
25
Pratella, David, Samira Ait-El-Mkadem Saadi, Sylvie Bannwarth, Véronique Paquis-Fluckinger, and Silvia Bottini. "A Survey of Autoencoder Algorithms to Pave the Diagnosis of Rare Diseases." International Journal of Molecular Sciences 22, no. 19 (2021): 10891. http://dx.doi.org/10.3390/ijms221910891.
Full textAbstract:
Rare diseases (RDs) concern a broad range of disorders and can result from various origins. For a long time, the scientific community was unaware of RDs. Impressive progress has already been made for certain RDs; however, due to the lack of sufficient knowledge, many patients are not diagnosed. Nowadays, the advances in high-throughput sequencing technologies such as whole genome sequencing, single-cell and others, have boosted the understanding of RDs. To extract biological meaning using the data generated by these methods, different analysis techniques have been proposed, including machine learning algorithms. These methods have recently proven to be valuable in the medical field. Among such approaches, unsupervised learning methods via neural networks including autoencoders (AEs) or variational autoencoders (VAEs) have shown promising performances with applications on various type of data and in different contexts, from cancer to healthy patient tissues. In this review, we discuss how AEs and VAEs have been used in biomedical settings. Specifically, we discuss their current applications and the improvements achieved in diagnostic and survival of patients. We focus on the applications in the field of RDs, and we discuss how the employment of AEs and VAEs would enhance RD understanding and diagnosis.
26
Radicioni, Luca, Francesco Morgan Bono, and Simone Cinquemani. "Vibration-Based Anomaly Detection in Industrial Machines: A Comparison of Autoencoders and Latent Spaces." Machines 13, no. 2 (2025): 139. https://doi.org/10.3390/machines13020139.
Full textAbstract:
In industrial settings, machinery components inevitably wear and degrade due to friction between moving parts. To address this, various maintenance strategies, including corrective, preventive, and predictive maintenance, are commonly employed. This paper focuses on predictive maintenance through vibration analysis, utilizing data-driven models. This study explores the application of unsupervised learning methods, particularly Convolutional Autoencoders (CAEs) and variational Autoencoders (VAEs), for anomaly detection (AD) in vibration signals. By transforming vibration signals into images using the Synchrosqueezing Transform (SST), this research leverages the strengths of convolutional neural networks (CNNs) in image processing, which have proven effective in AD, especially at the pixel level. The methodology involves training CAEs and VAEs on data from machinery in healthy condition and testing them on new data samples representing different levels of system degradation. The results indicate that models with spatial latent spaces outperform those with dense latent spaces in terms of reconstruction accuracy and AD capabilities. However, VAEs did not yield satisfactory results, likely because reconstruction-based metrics are not entirely useful for AD purposes in such models. This study also highlights the potential of ReLU residuals in enhancing the visibility of anomalies. The data used in this study are openly available.
27
Sengodan, Boopathi Chettiagounder, Prince Mary Stanislaus, Sivakumar Sabapathy Arumugam, et al. "Variational Autoencoders for Network Lifetime Enhancement in Wireless Sensors." Sensors 24, no. 17 (2024): 5630. http://dx.doi.org/10.3390/s24175630.
Full textAbstract:
Wireless sensor networks (WSNs) are structured for monitoring an area with distributed sensors and built-in batteries. However, most of their battery energy is consumed during the data transmission process. In recent years, several methodologies, like routing optimization, topology control, and sleep scheduling algorithms, have been introduced to improve the energy efficiency of WSNs. This study introduces a novel method based on a deep learning approach that utilizes variational autoencoders (VAEs) to improve the energy efficiency of WSNs by compressing transmission data. The VAE approach is customized in this work for compressing WSN data by retaining its important features. This is achieved by analyzing the statistical structure of the sensor data rather than providing a fixed-size latent representation. The performance of the proposed model is verified using a MATLAB simulation platform, integrating a pre-trained variational autoencoder model with openly available wireless sensor data. The performance of the proposed model is found to be satisfactory in comparison to traditional methods, like the compressed sensing technique, lightweight temporal compression, and the autoencoder, in terms of having an average compression rate of 1.5572. The WSN simulation also indicates that the VAE-incorporated architecture attains a maximum network lifetime of 1491 s and suggests that VAE could be used for compression-based transmission using WSNs, as its reconstruction rate is 0.9902, which is better than results from all the other techniques.
28
Yang, Zhihan, Anurag Sarkar, and Seth Cooper. "Game Level Clustering and Generation Using Gaussian Mixture VAEs." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 16, no. 1 (2020): 137–43. http://dx.doi.org/10.1609/aiide.v16i1.7422.
Full textAbstract:
Variational autoencoders (VAEs) have been shown to be able to generate game levels but require manual exploration of the learned latent space to generate outputs with desired attributes. While conditional VAEs address this by allowing generation to be conditioned on labels, such labels have to be provided during training and thus require prior knowledge which may not always be available. In this paper, we apply Gaussian Mixture VAEs (GMVAEs), a variant of the VAE which imposes a mixture of Gaussians (GM) on the latent space, unlike regular VAEs which impose a unimodal Gaussian. This allows GMVAEs to cluster levels in an unsupervised manner using the components of the GM and then generate new levels using the learned components. We demonstrate our approach with levels from Super Mario Bros., Kid Icarus and Mega Man. Our results show that the learned components discover and cluster level structures and patterns and can be used to generate levels with desired characteristics.
29
Xie, Yaopeng. "AI-driven automatic generation and rendering of game characters." Applied and Computational Engineering 82, no. 1 (2024): 137–41. http://dx.doi.org/10.54254/2755-2721/82/20241022.
Full textAbstract:
Abstract. This paper provides a comprehensive review of AI-driven techniques for the automatic generation and rendering of game characters, with a particular focus on Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). GANs, using adversarial training approaches, have revolutionized character development by producing incredibly realistic and aesthetically pleasing gaming characters. VAEs, despite frequently encountering issues like image blurriness, provide an alternate strategy that emphasizes diversity and originality in the generated content. Additionally, conditional models that enable more individualized and regulated character generation are explored, as well as hybrid models that combine the best features of both GANs and VAEs. The difficulties with mode collapse in GANs and the requirement for big datasets for both GANs and VAEs are also covered, along with some possible fixes like transfer learning and semi-supervised learning strategies. This analysis emphasizes the growing significance of AI-driven game character generation in the gaming industry by highlighting its current state, problems, and future directions.
30
Satyadhar Joshi. "Enhancing structured finance risk models (Leland-Toft and Box-Cox) using GenAI (VAEs GANs)." International Journal of Science and Research Archive 14, no. 1 (2025): 1618–30. https://doi.org/10.30574/ijsra.2025.14.1.0306.
Full textAbstract:
This work explores the integration of generative artificial intelligence (GenAI), specifically Variational Autoencoders (VAEs), into statistical and structural financial models, with a focus on the Leland-Toft and Box-Cox frameworks. We conduct a comprehensive review of these models, highlighting their use in financial risk analysis, bankruptcy prediction, and time-series forecasting. Through the integration of VAEs, we demonstrate their capability to enhance data generation, improve predictive accuracy, and enable robust validation of financial models, particularly in scenarios with scarce data. The application of VAEs to the Leland-Toft model facilitated the calculation of key financial metrics, including default spreads, credit spreads, and leverage ratios. Additionally, VAEs integrated with Box-Cox models generated latent features that correlated effectively with traditional financial factors, underscoring their utility in predictive modeling and survival analysis. This work provides a detailed overview of implementation pipelines, architecture diagrams, and model validation methods, offering a foundation for future research. Expanding on the use of VAEs, we propose incorporating advanced machine learning techniques and real-time data to further enhance model performance and revolutionize financial modeling.
31
Li, Zhongwei, Xue Zhu, Ziqi Xin, Fangming Guo, Xingshuai Cui, and Leiquan Wang. "Variational Generative Adversarial Network with Crossed Spatial and Spectral Interactions for Hyperspectral Image Classification." Remote Sensing 13, no. 16 (2021): 3131. http://dx.doi.org/10.3390/rs13163131.
Full textAbstract:
Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have been widely used in hyperspectral image classification (HSIC) tasks. However, the generated HSI virtual samples by VAEs are often ambiguous, and GANs are prone to the mode collapse, which lead the poor generalization abilities ultimately. Moreover, most of these models only consider the extraction of spectral or spatial features. They fail to combine the two branches interactively and ignore the correlation between them. Consequently, the variational generative adversarial network with crossed spatial and spectral interactions (CSSVGAN) was proposed in this paper, which includes a dual-branch variational Encoder to map spectral and spatial information to different latent spaces, a crossed interactive Generator to improve the quality of generated virtual samples, and a Discriminator stuck with a classifier to enhance the classification performance. Combining these three subnetworks, the proposed CSSVGAN achieves excellent classification by ensuring the diversity and interacting spectral and spatial features in a crossed manner. The superior experimental results on three datasets verify the effectiveness of this method.
32
Dittadi, Andrea, Frederik K. Drachmann, and Thomas Bolander. "Planning from Pixels in Atari with Learned Symbolic Representations." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 6 (2021): 4941–49. http://dx.doi.org/10.1609/aaai.v35i6.16627.
Full textAbstract:
Width-based planning methods have been shown to yield state-of-the-art performance in the Atari 2600 domain using pixel input. One successful approach, RolloutIW, represents states with the B-PROST boolean feature set. An augmented version of RolloutIW, pi-IW, shows that learned features can be competitive with handcrafted ones for width-based search. In this paper, we leverage variational autoencoders (VAEs) to learn features directly from pixels in a principled manner, and without supervision. The inference model of the trained VAEs extracts boolean features from pixels, and RolloutIW plans with these features. The resulting combination outperforms the original RolloutIW and human professional play on Atari 2600 and drastically reduces the size of the feature set.
33
Zhu, Jun-Jie, Ning-Jie Zhang, Ting Wei, and Hai-Feng Chen. "Enhancing Conformational Sampling for Intrinsically Disordered and Ordered Proteins by Variational Autoencoder." International Journal of Molecular Sciences 24, no. 8 (2023): 6896. http://dx.doi.org/10.3390/ijms24086896.
Full textAbstract:
Intrinsically disordered proteins (IDPs) account for more than 50% of the human proteome and are closely associated with tumors, cardiovascular diseases, and neurodegeneration, which have no fixed three-dimensional structure under physiological conditions. Due to the characteristic of conformational diversity, conventional experimental methods of structural biology, such as NMR, X-ray diffraction, and CryoEM, are unable to capture conformational ensembles. Molecular dynamics (MD) simulation can sample the dynamic conformations at the atomic level, which has become an effective method for studying the structure and function of IDPs. However, the high computational cost prevents MD simulations from being widely used for IDPs conformational sampling. In recent years, significant progress has been made in artificial intelligence, which makes it possible to solve the conformational reconstruction problem of IDP with fewer computational resources. Here, based on short MD simulations of different IDPs systems, we use variational autoencoders (VAEs) to achieve the generative reconstruction of IDPs structures and include a wider range of sampled conformations from longer simulations. Compared with the generative autoencoder (AEs), VAEs add an inference layer between the encoder and decoder in the latent space, which can cover the conformational landscape of IDPs more comprehensively and achieve the effect of enhanced sampling. Through experimental verification, the Cα RMSD between VAE-generated and MD simulation sampling conformations in the 5 IDPs test systems was significantly lower than that of AE. The Spearman correlation coefficient on the structure was higher than that of AE. VAE can also achieve excellent performance regarding structured proteins. In summary, VAEs can be used to effectively sample protein structures.
34
Akuzawa, Kei, Yusuke Iwasawa, and Yutaka Matsuo. "Information-theoretic regularization for learning global features by sequential VAE." Machine Learning 110, no. 8 (2021): 2239–66. http://dx.doi.org/10.1007/s10994-021-06032-4.
Full textAbstract:
AbstractSequential variational autoencoders (VAEs) with a global latent variable z have been studied for disentangling the global features of data, which is useful for several downstream tasks. To further assist the sequential VAEs in obtaining meaningful z, existing approaches introduce a regularization term that maximizes the mutual information (MI) between the observation and z. However, by analyzing the sequential VAEs from the information-theoretic perspective, we claim that simply maximizing the MI encourages the latent variable to have redundant information, thereby preventing the disentanglement of global features. Based on this analysis, we derive a novel regularization method that makes z informative while encouraging disentanglement. Specifically, the proposed method removes redundant information by minimizing the MI between z and the local features by using adversarial training. In the experiments, we trained two sequential VAEs, state-space and autoregressive model variants, using speech and image datasets. The results indicate that the proposed method improves the performance of downstream classification and data generation tasks, thereby supporting our information-theoretic perspective for the learning of global features.
35
Sidulova, Mariia, and Chung Hyuk Park. "Conditional Variational Autoencoder for Functional Connectivity Analysis of Autism Spectrum Disorder Functional Magnetic Resonance Imaging Data: A Comparative Study." Bioengineering 10, no. 10 (2023): 1209. http://dx.doi.org/10.3390/bioengineering10101209.
Full textAbstract:
Generative models, such as Variational Autoencoders (VAEs), are increasingly employed for atypical pattern detection in brain imaging. During training, these models learn to capture the underlying patterns within “normal” brain images and generate new samples from those patterns. Neurodivergent states can be observed by measuring the dissimilarity between the generated/reconstructed images and the input images. This paper leverages VAEs to conduct Functional Connectivity (FC) analysis from functional Magnetic Resonance Imaging (fMRI) scans of individuals with Autism Spectrum Disorder (ASD), aiming to uncover atypical interconnectivity between brain regions. In the first part of our study, we compare multiple VAE architectures—Conditional VAE, Recurrent VAE, and a hybrid of CNN parallel with RNN VAE—aiming to establish the effectiveness of VAEs in application FC analysis. Given the nature of the disorder, ASD exhibits a higher prevalence among males than females. Therefore, in the second part of this paper, we investigate if introducing phenotypic data could improve the performance of VAEs and, consequently, FC analysis. We compare our results with the findings from previous studies in the literature. The results showed that CNN-based VAE architecture is more effective for this application than the other models.
36
Miller, Tymoteusz, Irmina Durlik, Adrianna Łobodzińska, and Ewelina Kostecka. "GENERATIVE AI: A TOOL FOR ADDRESSING DATA SCARCITY IN SCIENTIFIC RESEARCH." Grail of Science, no. 43 (September 15, 2024): 301–7. http://dx.doi.org/10.36074/grail-of-science.06.09.2024.039.
Full textAbstract:
Generative AI, a pivotal advancement in data science, addresses data scarcity by producing high-quality synthetic data that mirrors real-world data. This article explores Generative AI's capabilities, including data augmentation, privacy-preserving anonymization, simulation of rare events, and cost-efficient data collection. Techniques such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) are discussed, highlighting their role in creating realistic and diverse synthetic data. The practical applications span healthcare, finance, and climate science, demonstrating Generative AI's transformative potential in enhancing research across various scientific disciplines.
37
Seberger, John S., and Aubrey Slaughter. "The Mystics and Magic of Latent Space: Becoming the Unseen." Magic, Vol. 5, no. 1 (2020): 88–93. http://dx.doi.org/10.47659/m8.088.art.
Full textAbstract:
Bridging concerns from human-computer interaction (HCI) and media studies, this essay theorizes deepfake images in terms of their phenomenological implications: the extent to which they enfold the human viewer in a world of the otherwise unseen. Drawing on comparative phenomenology of Vilém Flusser and Louis Bec, we focus on variational autoencoders (VAEs). We contend that the processes underlying deepfake image construction, as much as deepfake images themselves, evidence a parallel, prosthetic, and computational phenomenology: a study of “that which appears” to a computer, and which appears secondarily to a user-human as image. We use the example of VAEs to argue for the emergence of a second-order, received phenomenology of the augmented human as we reside in an increasingly computational world. Keywords: deepfake, computer vision, augmented reality, computer phenomenology, magic phenomenology, machine shamanism
38
J, Akarsh. "Language Enabled Image Originator." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem34747.
Full textAbstract:
Traditionally, forensic artists would painstakingly sketch a suspect's face from a witness's statement in order to create forensic photographs. There are restrictions on this procedure, though. First, it depends a great deal on the interpretation of the artist, which can bring falsehoods and prejudices. It can also take a lot of time, particularly if the drawing needs to be refined repeatedly. Image generation is the process of creating new pictures that are comparable to the people in a certain dataset. Producing visually realistic pictures that fit the input's properties is the aim of image creation. information. Machine learning employs a number of pictures generating approaches, such as auto-regressive models, variational autoencoders (VAEs), generative adversarial networks (GANs), and stable diffusion models. These models are trained on an image dataset (for instance, 5,85B CLIP-filtered image-text pairings make up the large-scale research dataset LAION 5B) and are taught to produce new pictures that are comparable to the original data. An image generating model may be used to create a series of pictures for forensic sketching, with the witness's description serving as the basis for selecting the best image. This and the necessary face feature changes may be fed into the Image-to-Image Translation model. Until an adequate picture is produced, the picture-to-Image Translation model creates a fresh series of images with alterations. Key Words: variational autoencoders (VAEs), Generative adversarial networks (GANs),
39
Feugang Nteumagné, Bienvenue, Hermann Azemtsa Donfack, and Celestin Wafo Soh. "Variational Autoencoders for Completing the Volatility Surfaces." Journal of Risk and Financial Management 18, no. 5 (2025): 239. https://doi.org/10.3390/jrfm18050239.
Full textAbstract:
Variational autoencoders (VAEs) have emerged as a promising tool for modeling volatility surfaces, with particular significance for generating synthetic implied volatility scenarios that enhance risk management capabilities. This study evaluates VAE performance using synthetic volatility surfaces, chosen specifically for their arbitrage-free properties and clean data characteristics. Through a comprehensive comparison with traditional methods including thin-plate spline interpolation, parametric models (SABR and SVI), and deterministic autoencoders, we demonstrate that our VAE approach with latent space optimization consistently outperforms existing methods, particularly in scenarios with extreme data sparsity. Our findings show that accurate, arbitrage-free surface reconstruction is achievable using only 5% of the original data points, with errors 7–12 times lower than competing approaches in high-sparsity scenarios. We rigorously validate the preservation of critical no-arbitrage conditions through probability distribution analysis and total variance strip non-intersection tests. The framework we develop overcomes traditional barriers of limited market data by generating over 13,500 synthetic surfaces for training, compared to typical market availability of fewer than 100. These capabilities have important implications for market risk analysis, derivatives pricing, and the development of more robust risk management frameworks, particularly in emerging markets or for newly introduced derivatives where historical data are scarce. Our integration of machine learning with financial theory constraints represents a significant advancement in volatility surface modeling that balances statistical accuracy with financial relevance.
40
Ye, Fei, and Adrian G. Bors. "Lifelong Generative Modelling Using Dynamic Expansion Graph Model." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 8 (2022): 8857–65. http://dx.doi.org/10.1609/aaai.v36i8.20867.
Full textAbstract:
Variational Autoencoders (VAEs) suffer from degenerated performance, when learning several successive tasks. This is caused by catastrophic forgetting. In order to address the knowledge loss, VAEs are using either Generative Replay (GR) mechanisms or Expanding Network Architectures (ENA). In this paper we study the forgetting behaviour of VAEs using a joint GR and ENA methodology, by deriving an upper bound on the negative marginal log-likelihood. This theoretical analysis provides new insights into how VAEs forget the previously learnt knowledge during lifelong learning. The analysis indicates the best performance achieved when considering model mixtures, under the ENA framework, where there are no restrictions on the number of components. However, an ENA-based approach may require an excessive number of parameters. This motivates us to propose a novel Dynamic Expansion Graph Model (DEGM). DEGM expands its architecture, according to the novelty associated with each new database, when compared to the information already learnt by the network from previous tasks. DEGM training optimizes knowledge structuring, characterizing the joint probabilistic representations corresponding to the past and more recently learned tasks. We demonstrate that DEGM guarantees optimal performance for each task while also minimizing the required number of parameters.
41
Liu, Yijing, Shuyu Lin, and Ronald Clark. "Towards Consistent Variational Auto-Encoding (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 10 (2020): 13869–70. http://dx.doi.org/10.1609/aaai.v34i10.7207.
Full textAbstract:
Variational autoencoders (VAEs) have been a successful approach to learning meaningful representations of data in an unsupervised manner. However, suboptimal representations are often learned because the approximate inference model fails to match the true posterior of the generative model, i.e. an inconsistency exists between the learnt inference and generative models. In this paper, we introduce a novel consistency loss that directly requires the encoding of the reconstructed data point to match the encoding of the original data, leading to better representations. Through experiments on MNIST and Fashion MNIST, we demonstrate the existence of the inconsistency in VAE learning and that our method can effectively reduce such inconsistency.
42
Thorne, Ben, Lloyd Knox, and Karthik Prabhu. "A generative model of galactic dust emission using variational autoencoders." Monthly Notices of the Royal Astronomical Society 504, no. 2 (2021): 2603–13. http://dx.doi.org/10.1093/mnras/stab1011.
Full textAbstract:
ABSTRACT Emission from the interstellar medium can be a significant contaminant of measurements of the intensity and polarization of the cosmic microwave background (CMB). For planning CMB observations, and for optimizing foreground-cleaning algorithms, a description of the statistical properties of such emission can be helpful. Here, we examine a machine learning approach to inferring the statistical properties of dust from observational data. In particular, we apply a type of neural network called a variational autoencoder (VAE) to maps of the intensity of emission from interstellar dust as inferred from Planck sky maps and demonstrate its ability to (i) simulate new samples with similar summary statistics as the training set, (ii) provide fits to emission maps withheld from the training set, and (iii) produce constrained realizations. We find VAEs are easier to train than another popular architecture: that of generative adversarial networks, and are better suited for use in Bayesian inference.
43
Santosh, Kumar. "Generative AI in the Categorisation of Paediatric Pneumonia on Chest Radiographs." International Journal of Current Science Research and Review 08, no. 02 (2025): 712–17. https://doi.org/10.5281/zenodo.14843157.
Full textAbstract:
Abstract : Paediatric pneumonia is a leading cause of morbidity and mortality worldwide, necessitating accurate and timely diagnosis. This study explores the application of Generative AI for categorising paediatric pneumonia using chest radiographs. Leveraging deep learning techniques, including Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), we enhance image quality, generate synthetic training data, and improve model generalizability. The proposed framework integrates AI-driven feature extraction, convolutional neural networks (CNNs), and attention mechanisms to improve diagnostic accuracy. The results demonstrate significant improvements in classification performance compared to traditional methods, with a focus on interpretability and clinical usability.
44
Obi, E. D., J. A. Yentumi, D. Mbatuegwu, O. I. Omotuyi, O. O. Ajayi, and A. Nwokoro. "LAIgnd: Revolutionizing Drug Discovery with Advanced AI-Driven Molecule Generation." Advances in Multidisciplinary & Scientific Research Journal Publication 15, no. 4 (2024): 1–10. http://dx.doi.org/10.22624/aims/cisdi/v15n3p4.
Full textAbstract:
De novo molecular generation is crucial for advancing drug discovery and chemical research. This accelerates the search for new drug candidates and deepens our understanding of molecular diversity. The development of deep learning has propelled and expedited the de novo molecular generation. Generative networks, particularly Variational Autoencoders (VAEs), can randomly produce new molecules and modify molecular structures to enhance specific chemical properties, which are essential for advancing drug discovery. Although VAEs offer numerous advantages, they are hindered by limitations that affect their capacity to optimize properties and decode syntactically valid molecules. To address these challenges, we present LAIgnd, a de novo drug molecule generation model that implements a custom β-CVAE architecture conditioned on protein sequences and SELFIES input. Extensive experiments have shown that LAIgnd generates a wide variety of valid, novel, and effective molecules for complex and simple diseases, demonstrating its robustness and generalization capabilities. Additionally, by employing molecular docking, toxicity, similarity, and synthetic accessibility experiments, we demonstrated the drug-likeness and effectiveness of the generated molecules. The ability of our model to generate novel and diverse compounds was illustrated by a case study focusing on Lung Cancer. A total of four hundred (400) molecules were generated by LAIgnd, with a high number of molecules exhibiting strong inhibitory activity against the Epidermal Growth Factor receptor, as indicated by binding affinities. LAIgnd provides new insights into future directions to enhance therapeutics for complex and simple diseases by generating high-quality multi-target molecules for drug discovery. Key words: De novo molecular generation, Drug discovery, Variational Autoencoders (VAEs), SELFIES, Protein sequences. CISDI Journal Reference Format Obi, E.D., Yentumi, J.A., Mbatuegwu, D., Omotuyi, O.I., Ajayi, O.O. & Nwokoro, A. (2024): LAIgnd: Revolutionizing Drug Discovery with Advanced AI-Driven Molecule Generation. Computing, Information Systems, Development Informatics & Allied Research Journal. Vol 15 No 4, Pp 1-10. Available online at www.isteams.net/cisdijournal. dx.doi.org/10.22624/AIMS/CISDI/V15N3P4
45
Sadiq, Saad, Mei-Ling Shyu, and Daniel J. Feaster. "Counterfactual Autoencoder for Unsupervised Semantic Learning." International Journal of Multimedia Data Engineering and Management 9, no. 4 (2018): 1–20. http://dx.doi.org/10.4018/ijmdem.2018100101.
Full textAbstract:
Deep Neural Networks (DNNs) are best known for being the state-of-the-art in artificial intelligence (AI) applications including natural language processing (NLP), speech processing, computer vision, etc. In spite of all recent achievements of deep learning, it has yet to achieve semantic learning required to reason about the data. This lack of reasoning is partially imputed to the boorish memorization of patterns and curves from millions of training samples and ignoring the spatiotemporal relationships. The proposed framework puts forward a novel approach based on variational autoencoders (VAEs) by using the potential outcomes model and developing the counterfactual autoencoders. The proposed framework transforms any sort of multimedia input distributions to a meaningful latent space while giving more control over how the latent space is created. This allows us to model data that is better suited to answer inference-based queries, which is very valuable in reasoning-based AI applications.
46
Papadopoulos, Dimitris, and Vangelis D. Karalis. "Introducing an Artificial Neural Network for Virtually Increasing the Sample Size of Bioequivalence Studies." Applied Sciences 14, no. 7 (2024): 2970. http://dx.doi.org/10.3390/app14072970.
Full textAbstract:
Sample size is a key factor in bioequivalence and clinical trials. An appropriately large sample is necessary to gain valuable insights into a designated population. However, large sample sizes lead to increased human exposure, costs, and a longer time for completion. In a previous study, we introduced the idea of using variational autoencoders (VAEs), a type of artificial neural network, to synthetically create in clinical studies. In this work, we further elaborate on this idea and expand it in the field of bioequivalence (BE) studies. A computational methodology was developed, combining Monte Carlo simulations of 2 × 2 crossover BE trials with deep learning algorithms, specifically VAEs. Various scenarios, including variability levels, the actual sample size, the VAE-generated sample size, and the difference in performance between the two pharmaceutical products under comparison, were explored. All simulations showed that incorporating AI generative algorithms for creating virtual populations in BE trials has many advantages, as less actual human data can be used to achieve similar, and even better, results. Overall, this work shows how the application of generative AI algorithms, like VAEs, in clinical/bioequivalence studies can be a modern tool to significantly reduce human exposure, costs, and trial completion time.
47
Zou, Jincheng, Guorong Chen, Jian Wang, Bao Zhang, Hong Hu, and Cong Liu. "A Hierarchical Latent Modulation Approach for Controlled Text Generation." Mathematics 13, no. 5 (2025): 713. https://doi.org/10.3390/math13050713.
Full textAbstract:
Generative models based on Variational Autoencoders (VAEs) represent an important area of research in Controllable Text Generation (CTG). However, existing approaches often do not fully exploit the potential of latent variables, leading to limitations in both the diversity and thematic consistency of the generated text. To overcome these challenges, this paper introduces a new framework based on Hierarchical Latent Modulation (HLM). The framework incorporates a hierarchical latent space modulation module for the generation and embedding of conditional modulation parameters. By using low-rank tensor factorization (LMF), the approach combines multi-layer latent variables and generates modulation parameters based on conditional labels, enabling precise control over the features during text generation. Additionally, layer-by-layer normalization and random dropout mechanisms are employed to address issues such as the under-utilization of conditional information and the collapse of generative patterns. We performed experiments on five baseline models based on VAEs for conditional generation, and the results demonstrate the effectiveness of the proposed framework.
48
Zhou, Jingxi. "Text to Image Generation: A Literature Review Focus on the Diffusion Model." ITM Web of Conferences 73 (2025): 02037. https://doi.org/10.1051/itmconf/20257302037.
Full textAbstract:
This paper reviews the progress in text-to-image generation, which enables the creation of images from textual descriptions. This technology holds promise across various fields, including creative arts, gaming, and healthcare. The main approaches in this area are Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models (DM). While GANs initially made significant advancements in realistic image generation, they faced issues with stability and diversity. VAEs introduced a probabilistic approach, allowing for diverse outputs but often at the cost of image quality. The development of DM, like Stable Diffusion, Imagen, and DALL-E 2, has addressed many limitations, producing high-quality, coherent images through iterative denoising. DM stands out for its stability and ability to generate detailed, semantically accurate images. This review explores the strengths and limitations of each approach, with an emphasis on the advantages of DM. It also discusses future directions, including improving efficiency, enhancing multimodal capabilities, and reducing data requirements to make these models more accessible and versatile for various applications.
49
Huang, Jing, and Tao Duan. "Deep learning-based approaches for cellular mechanics analysis and secure data sharing in biomechanics." Molecular & Cellular Biomechanics 22, no. 4 (2025): 1059. https://doi.org/10.62617/mcb1059.
Full textAbstract:
Cellular mechanics behavior, encompassing properties such as elasticity, viscosity, and stress-strain responses, is fundamental to understanding disease mechanisms, tissue regeneration, and drug development. This study proposes a deep learning-based framework integrating Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and federated learning to model and analyze cellular mechanics while enabling secure data sharing. The proposed methods preserve critical biomechanical insights, such as force-displacement curves and cellular deformation patterns, while mitigating re-identification risks during multi-institutional collaborations. Experimental evaluations demonstrate the framework’s effectiveness in maintaining data utility and analytical accuracy, paving the way for advancing biomechanics research and fostering applications in regenerative medicine and tissue engineering.
50
Adithya Jakkaraju, Venugopal Muraleedharan Mini. "Ethical Synthetic Data Generation via Fairness-Aware Generative Models." Journal of Information Systems Engineering and Management 10, no. 24s (2025): 740–52. https://doi.org/10.52783/jisem.v10i24s.3988.
Full textAbstract:
Synthetic data has emerged as a crucial component in AI model training, offering privacy protection and enhanced data diversity. However, generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) often inherit and amplify biases present in training datasets, leading to ethical concerns. This paper explores fairness-aware generative models that embed fairness constraints (e.g., demographic parity, equalized odds) to mitigate bias during data synthesis. We review methods for bias quantification in synthetic data, regulatory compliance frameworks, and algorithmic advancements in fair synthetic data generation. The research also presents an evaluation framework for fairness, utility, and privacy trade-offs, followed by a discussion on future research directions.