Log in

Relevant bibliographies by topics / Inference training / Journal articles

To see the other types of publications on this topic, follow the link: Inference training.

Journal articles on the topic 'Inference training'

Author: Grafiati

Published: 2 June 2025

Last updated: 31 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Inference training.'

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

Melgarejo, Teófilo Félix Valentín, Pablo Lenin La Madrid Vivar, Clodoaldo Ramos Pando, Pablo Lolo Valentín Melgarejo, and Agustín Arturo Aguirre Adauto. "Inference and reading comprehension in university students." Nurture 18, no. 4 (2024): 785–94. http://dx.doi.org/10.55951/nurture.v18i4.846.

Full text

Abstract:

Purpose: The objective of this research was to determine the relationship between inference and reading comprehension. We sought to verify the relationship between inductive and deductive inferences in the comprehensive reading of Daniel Alcides Carrión National University Peru students majoring in communication and literature. Design/Methodology/Approach: The correlational-explanatory research design was used since the correlation of the study variables was sought through scientific and specifically analytical, deductive and interpretive methodology on a population of 104 and the probabilisti

APA, Harvard, Vancouver, ISO, and other styles

2

Liu, Yu, Anurag Andhare, and Kyoung-Don Kang. "Corun: Concurrent Inference and Continuous Training at the Edge for Cost-Efficient AI-Based Mobile Image Sensing." Sensors 24, no. 16 (2024): 5262. http://dx.doi.org/10.3390/s24165262.

Full text

Abstract:

Intelligent mobile image sensing powered by deep learning analyzes images captured by cameras from mobile devices, such as smartphones or smartwatches. It supports numerous mobile applications, such as image classification, face recognition, and camera scene detection. Unfortunately, mobile devices often lack the resources necessary for deep learning, leading to increased inference latency and rapid battery consumption. Moreover, the inference accuracy may decline over time due to potential data drift. To address these issues, we introduce a new cost-efficient framework, called Corun, designed

APA, Harvard, Vancouver, ISO, and other styles

3

Yu, Kai, and Mark J. F. Gales. "Bayesian Adaptive Inference and Adaptive Training." IEEE Transactions on Audio, Speech and Language Processing 15, no. 6 (2007): 1932–43. http://dx.doi.org/10.1109/tasl.2007.901300.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

MIH, Viorel, and Codruța MIH. "Text-Based Inference Instruction for Elementary Grade Children with Reading Comprehension Difficulties: An Intervention Research." Studia Universitatis Babeș-Bolyai Psychologia-Paedagogia 69, no. 1 (2024): 257–72. http://dx.doi.org/10.24193/subbpsyped.2024.1.13.

Full text

Abstract:

"The current study investigated the effects of inference instruction on text-based inferences by third graders who are below average in reading comprehension but average in reading fluency and cognitive abilities. Text-based inferences occur when the preceding text has an identifiable causal antecedent. Participants were randomly assigned and attended twelve 30-minute sessions of the inferences training intervention. We have included strategies for integrating information from the text to improve reading comprehension skills. We provide an overview of how specific text-based instruction influe

APA, Harvard, Vancouver, ISO, and other styles

5

Zhao, Yanchao, Jiale Chen, Jiale Zhang, et al. "User-Level Membership Inference for Federated Learning in Wireless Network Environment." Wireless Communications and Mobile Computing 2021 (October 19, 2021): 1–17. http://dx.doi.org/10.1155/2021/5534270.

Full text

Abstract:

With the rise of privacy concerns in traditional centralized machine learning services, federated learning, which incorporates multiple participants to train a global model across their localized training data, has lately received significant attention in both industry and academia. Bringing federated learning into a wireless network scenario is a great move. The combination of them inspires tremendous power and spawns a number of promising applications. Recent researches reveal the inherent vulnerabilities of the various learning modes for the membership inference attacks that the adversary c

APA, Harvard, Vancouver, ISO, and other styles

6

Oyekan, Basirat. "DEVELOPING PRIVACY-PRESERVING FEDERATED LEARNING MODELS FOR COLLABORATIVE HEALTH DATA ANALYSIS ACROSS MULTIPLE INSTITUTIONS WITHOUT COMPROMISING DATA SECURITY." Journal of Knowledge Learning and Science Technology ISSN: 2959-6386 (online) 3, no. 3 (2024): 139–64. http://dx.doi.org/10.60087/jklst.vol3.n3.p139-164.

Full text

Abstract:

Federated learning is an emerging distributed machine learning technique that enables collaborative training of models among devices and servers without exchanging private data. However, several privacy and security risks associated with federated learning need to be addressed for safe adoption. This review provides a comprehensive analysis of the key threats in federated learning and the mitigation strategies used to overcome these threats. Some of the major threats identified include model inversion, membership inference, data attribute inference and model extraction attacks. Model inversion

APA, Harvard, Vancouver, ISO, and other styles

7

Vishakha, Agrawal. "Demystifying Deep Learning Compiler Optimizations for Training and Inference." Journal of Advances in Developmental Research 12, no. 2 (2021): 1–9. https://doi.org/10.5281/zenodo.14551855.

Full text

Abstract:

Deep learning has achieved tremendous success in recent years, powering many artificial intelligence applications. However, deep learning models are computationally intensive to train, requiring massive amounts of data and compute resources. Once trained, deep learning models need to be deployed for inference to make predictions on new data. Hardware used for training differs from hardware used for inference. Deep learning compilers have revolutionized the field of artificial intelligence by optimizing the performance of deep learning models on various hardware platforms. In the current landsc

APA, Harvard, Vancouver, ISO, and other styles

8

Suri, Anshuman, and David Evans. "Formalizing and Estimating Distribution Inference Risks." Proceedings on Privacy Enhancing Technologies 2022, no. 4 (2022): 528–51. http://dx.doi.org/10.56553/popets-2022-0121.

Full text

Abstract:

Distribution inference, sometimes called property inference, infers statistical properties about a training set from access to a model trained on that data. Distribution inference attacks can pose serious risks when models are trained on private data, but are difficult to distinguish from the intrinsic purpose of statistical machine learning—namely, to produce models that capture statistical properties about a distribution. Motivated by Yeom et al.’s membership inference framework, we propose a formal definition of distribution inference attacks general enough to describe a broad class of atta

APA, Harvard, Vancouver, ISO, and other styles

9

Shafique, Muhammad Ali, Arslan Munir, and Joonho Kong. "Deep Learning Performance Characterization on GPUs for Various Quantization Frameworks." AI 4, no. 4 (2023): 926–48. http://dx.doi.org/10.3390/ai4040047.

Full text

Abstract:

Deep learning is employed in many applications, such as computer vision, natural language processing, robotics, and recommender systems. Large and complex neural networks lead to high accuracy; however, they adversely affect many aspects of deep learning performance, such as training time, latency, throughput, energy consumption, and memory usage in the training and inference stages. To solve these challenges, various optimization techniques and frameworks have been developed for the efficient performance of deep learning models in the training and inference stages. Although optimization techn

APA, Harvard, Vancouver, ISO, and other styles

10

Yang, Chao-Han Huck, I.-Te Danny Hung, Yi Ouyang, and Pin-Yu Chen. "Training a Resilient Q-network against Observational Interference." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 8 (2022): 8814–22. http://dx.doi.org/10.1609/aaai.v36i8.20862.

Full text

Abstract:

Deep reinforcement learning (DRL) has demonstrated impressive performance in various gaming simulators and real-world applications. In practice, however, a DRL agent may receive faulty observation by abrupt interferences such as black-out, frozen-screen, and adversarial perturbation. How to design a resilient DRL algorithm against these rare but mission-critical and safety-crucial scenarios is an essential yet challenging task. In this paper, we consider a deep q-network (DQN) framework training with an auxiliary task of observational interferences such as artificial noises. Inspired by causal

APA, Harvard, Vancouver, ISO, and other styles

11

Terenchuk, Svitlana, Yuliia Riabchun, and Maksym Delembovskyi. "IDENTIFICATION OF ENTRANT’S ABILITIES ON THE BASIS OF SUGENO-TYPE FUZZY INFERENCE SYSTEMS." Aviation 26, no. 4 (2022): 176–82. http://dx.doi.org/10.3846/aviation.2022.17636.

Full text

Abstract:

In the conditions of effective training in aviation for dispatchers and pilots, it requires the use of infocommunication systems capable of working under conditions of fuzzy uncertainty in real time. The functioning of such systems is based on fuzzy inference systems. However, the development and implementation of these systems requires the creation of fuzzy knowledge bases. Therefore, special attention in this study is paid to the creation of a system of fuzzy inferences and the formation of a fuzzy knowledge base of this system. The result is a lozenge-type fuzzy inference system. The fuzzy

APA, Harvard, Vancouver, ISO, and other styles

12

Vu, Thang, Haeyong Kang, and Chang D. Yoo. "SCNet: Training Inference Sample Consistency for Instance Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 3 (2021): 2701–9. http://dx.doi.org/10.1609/aaai.v35i3.16374.

Full text

Abstract:

Cascaded architectures have brought significant performance improvement in object detection and instance segmentation. However, there are lingering issues regarding the disparity in the Intersection-over-Union (IoU) distribution of the samples between training and inference. This disparity can potentially exacerbate detection accuracy. This paper proposes an architecture referred to as Sample Consistency Network (SCNet) to ensure that the IoU distribution of the samples at training time is close to that at inference time. Furthermore, SCNet incorporates feature relay and utilizes global contex

APA, Harvard, Vancouver, ISO, and other styles

13

Anastasopoulos, Nikolaos, Ioannis G. Tsoulos, Evangelos Dermatas, and Evangelos Karvounis. "Language Inference Using Elman Networks with Evolutionary Training." Signals 3, no. 3 (2022): 611–19. http://dx.doi.org/10.3390/signals3030037.

Full text

Abstract:

In this paper, a novel Elman-type recurrent neural network (RNN) is presented for the binary classification of arbitrary symbol sequences, and a novel training method, including both evolutionary and local search methods, is evaluated using sequence databases from a wide range of scientific areas. An efficient, publicly available, software tool is implemented in C++, accelerating significantly (more than 40 times) the RNN weights estimation process using both simd and multi-thread technology. The experimental results, in all databases, with the hybrid training method show improvements in a ran

APA, Harvard, Vancouver, ISO, and other styles

14

Huertas-Tato, Javier, Alejandro Martín, and David Camacho. "SILT: Efficient transformer training for inter-lingual inference." Expert Systems with Applications 200 (August 2022): 116923. http://dx.doi.org/10.1016/j.eswa.2022.116923.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Cawston, Alvina, Jennifer L. Callahan, and Elizabeth R. Wrape. "Pre-practicum training to facilitate social inference competency." Training and Education in Professional Psychology 9, no. 1 (2015): 28–34. http://dx.doi.org/10.1037/tep0000069.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Gu, Yuechun, and Keke Chen. "GAN-Based Domain Inference Attack." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 12 (2023): 14214–22. http://dx.doi.org/10.1609/aaai.v37i12.26663.

Full text

Abstract:

Model-based attacks can infer training data information from deep neural network models. These attacks heavily depend on the attacker's knowledge of the application domain, e.g., using it to determine the auxiliary data for model-inversion attacks. However, attackers may not know what the model is used for in practice. We propose a generative adversarial network (GAN) based method to explore likely or similar domains of a target model -- the model domain inference (MDI) attack. For a given target (classification) model, we assume that the attacker knows nothing but the input and output formats

APA, Harvard, Vancouver, ISO, and other styles

17

Rafique, Samina, M. Najam-ul-Islam, M. Shafique, and A. Mahmood. "Neuro-fuzzy control of sit-to-stand motion using head position tracking." Measurement and Control 53, no. 7-8 (2020): 1342–53. http://dx.doi.org/10.1177/0020294020938079.

Full text

Abstract:

Based on the clinical evidence that head position measured by the multisensory system contributes to motion control, this study suggests a biomechanical human-central nervous system modeling and control framework for sit-to-stand motion synthesis. Motivated by the evidence for a task-oriented encoding of motion by the central nervous system, we propose a framework to synthesize and control sit-to-stand motion using only head position trajectory in the high-level-task-control environment. First, we design a generalized analytical framework comprising a human biomechanical model and an adaptive

APA, Harvard, Vancouver, ISO, and other styles

18

Berens, Sam C., and Chris M. Bird. "Hippocampal and medial prefrontal cortices encode structural task representations following progressive and interleaved training schedules." PLOS Computational Biology 18, no. 10 (2022): e1010566. http://dx.doi.org/10.1371/journal.pcbi.1010566.

Full text

Abstract:

Memory generalisations may be underpinned by either encoding- or retrieval-based generalisation mechanisms and different training schedules may bias some learners to favour one of these mechanisms over the other. We used a transitive inference task to investigate whether generalisation is influenced by progressive vs randomly interleaved training, and overnight consolidation. On consecutive days, participants learnt pairwise discriminations from two transitive hierarchies before being tested during fMRI. Inference performance was consistently better following progressive training, and for pair

APA, Harvard, Vancouver, ISO, and other styles

19

Moldoveanu, Matei, and Abdellatif Zaidi. "In-Network Learning: Distributed Training and Inference in Networks." Entropy 25, no. 6 (2023): 920. http://dx.doi.org/10.3390/e25060920.

Full text

Abstract:

In this paper, we study distributed inference and learning over networks which can be modeled by a directed graph. A subset of the nodes observes different features, which are all relevant/required for the inference task that needs to be performed at some distant end (fusion) node. We develop a learning algorithm and an architecture that can combine the information from the observed distributed features, using the processing units available across the networks. In particular, we employ information-theoretic tools to analyze how inference propagates and fuses across a network. Based on the insi

APA, Harvard, Vancouver, ISO, and other styles

20

Liu, Zili, Tu Zheng, Guodong Xu, Zheng Yang, Haifeng Liu, and Deng Cai. "Training-Time-Friendly Network for Real-Time Object Detection." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (2020): 11685–92. http://dx.doi.org/10.1609/aaai.v34i07.6838.

Full text

Abstract:

Modern object detectors can rarely achieve short training time, fast inference speed, and high accuracy at the same time. To strike a balance among them, we propose the Training-Time-Friendly Network (TTFNet). In this work, we start with light-head, single-stage, and anchor-free designs, which enable fast inference speed. Then, we focus on shortening training time. We notice that encoding more training samples from annotated boxes plays a similar role as increasing batch size, which helps enlarge the learning rate and accelerate the training process. To this end, we introduce a novel approach

APA, Harvard, Vancouver, ISO, and other styles

21

Valvano, Gabriele, Andrea Leo, and Sotirios A. Tsaftaris. "Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts." Machine Learning for Biomedical Imaging 1, MICCAI 2021 workshop omnibus (2022): 1–27. http://dx.doi.org/10.59275/j.melba.2022-bd5e.

Full text

Abstract:

Thanks to their ability to learn flexible data-driven losses, Generative Adversarial Networks (GANs) are an integral part of many semi- and weakly-supervised methods for medical image segmentation. GANs jointly optimise a generator and an adversarial discriminator on a set of training data. After training is complete, the discriminator is usually discarded, and only the generator is used for inference. But should we discard discriminators? In this work, we argue that training stable discriminators produces expressive loss functions that we can re-use at inference to detect and correct segmenta

APA, Harvard, Vancouver, ISO, and other styles

22

Yang, Dengtian, Lan Chen, Xiaoran Hao, and Yiheng Zhang. "Object Detection Post Processing Accelerator Based on Co-Design of Hardware and Software." Information 16, no. 1 (2025): 63. https://doi.org/10.3390/info16010063.

Full text

Abstract:

Deep learning significantly advances object detection. Post processes, a critical component of this process, select valid bounding boxes to represent the true targets during inference and assign boxes and labels to these objects during training to optimize the loss function. However, post processes constitute a substantial portion of the total processing time for a single image. This inefficiency primarily arises from the extensive Intersection over Union (IoU) calculations required between numerous redundant bounding boxes in post processing algorithms. To reduce these redundant IoU calculati

APA, Harvard, Vancouver, ISO, and other styles

23

Wang, Xiuling, and Wendy Hui Wang. "Subgraph Structure Membership Inference Attacks against Graph Neural Networks." Proceedings on Privacy Enhancing Technologies 2024, no. 4 (2024): 268–90. http://dx.doi.org/10.56553/popets-2024-0116.

Full text

Abstract:

Graph Neural Networks (GNNs) have been widely applied to various applications across different domains. However, recent studies have shown that GNNs are susceptible to the membership inference attacks (MIAs) which aim to infer if some particular data samples were included in the model’s training data. While most previous MIAs have focused on inferring the membership of individual nodes and edges within the training graph, we introduce a novel form of membership inference attack called the Structure Membership Inference Attack (SMIA) which aims to determine whether a given set of nodes correspo

APA, Harvard, Vancouver, ISO, and other styles

24

Zheng, Yangyang, Bin He, and Tianling Li. "Research on the Lightweight Deployment Method of Integration of Training and Inference in Artificial Intelligence." Applied Sciences 12, no. 13 (2022): 6616. http://dx.doi.org/10.3390/app12136616.

Full text

Abstract:

In recent years, the continuous development of artificial intelligence has largely been driven by algorithms and computing power. This paper mainly discusses the training and inference methods of artificial intelligence from the perspective of computing power. To address the issue of computing power, it is necessary to consider performance, cost, power consumption, flexibility, and robustness comprehensively. At present, the training of artificial intelligence models mostly are based on GPU platforms. Although GPUs offer high computing performance, their power consumption and cost are relative

APA, Harvard, Vancouver, ISO, and other styles

25

Zeng, Ziqian, Yihuai Hong, Hongliang Dai, Huiping Zhuang, and Cen Chen. "ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 17 (2024): 19506–14. http://dx.doi.org/10.1609/aaai.v38i17.29922.

Full text

Abstract:

Early Exiting is one of the most popular methods to achieve efficient inference. Current early exiting methods adopt the (weighted) sum of the cross entropy loss of all internal classifiers as the objective function during training, imposing all these classifiers to predict all instances correctly. However, during inference, as long as one internal classifier predicts an instance correctly, it can accelerate without losing accuracy. Thus, there is a notable gap between training and inference. We propose ConsistentEE, an early exiting method that is consistent in training and inference. Consist

APA, Harvard, Vancouver, ISO, and other styles

26

Dandi, Yatin, Homanga Bharadhwaj, Abhishek Kumar, and Piyush Rai. "Generalized Adversarially Learned Inference." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 8 (2021): 7185–92. http://dx.doi.org/10.1609/aaai.v35i8.16883.

Full text

Abstract:

Allowing effective inference of latent vectors while training GANs can greatly increase their applicability in various downstream tasks. Recent approaches, such as ALI and BiGAN frameworks, develop methods of inference of latent variables in GANs by adversarially training an image generator along with an encoder to match two joint distributions of image and latent vector pairs. We generalize these approaches to incorporate multiple layers of feedback on reconstructions, self-supervision, and other forms of supervision based on prior or learned knowledge about the desired solutions. We achieve

APA, Harvard, Vancouver, ISO, and other styles

27

Harun, Rashed, Eric Yang, Nastya Kassir, Wenhui Zhang, and James Lu. "Machine Learning for Exposure-Response Analysis: Methodological Considerations and Confirmation of Their Importance via Computational Experimentations." Pharmaceutics 15, no. 5 (2023): 1381. http://dx.doi.org/10.3390/pharmaceutics15051381.

Full text

Abstract:

Exposure-response (E-R) is a key aspect of pharmacometrics analysis that supports drug dose selection. Currently, there is a lack of understanding of the technical considerations necessary for drawing unbiased estimates from data. Due to recent advances in machine learning (ML) explainability methods, ML has garnered significant interest for causal inference. To this end, we used simulated datasets with known E-R “ground truth” to generate a set of good practices for the development of ML models required to avoid introducing biases when performing causal inference. These practices include the

APA, Harvard, Vancouver, ISO, and other styles

28

Li, Jie, Chang Tang, Zhechao Lei, et al. "KRA: K-Nearest Neighbor Retrieval Augmented Model for Text Classification." Electronics 13, no. 16 (2024): 3237. http://dx.doi.org/10.3390/electronics13163237.

Full text

Abstract:

Text classification is a fundamental task in natural language processing (NLP). Deep-learning-based text classification methods usually have two stages: training and inference. However, the training dataset is only used in the training stage. To make full use of the training dataset in the inference stage in order to improve model performance, we propose a k-nearest neighbors retrieval augmented method (KRA) for deep-learning-based text classification models. KRA works by first constructing a storage system that stores the embeddings of the training samples during the training stage. During th

APA, Harvard, Vancouver, ISO, and other styles

29

Liu, Zhenpeng, Ruilin Li, Dewei Miao, Lele Ren, and Yonggang Zhao. "Membership Inference Defense in Distributed Federated Learning Based on Gradient Differential Privacy and Trust Domain Division Mechanisms." Security and Communication Networks 2022 (July 14, 2022): 1–14. http://dx.doi.org/10.1155/2022/1615476.

Full text

Abstract:

Distributed federated learning models are vulnerable to membership inference attacks (MIA) because they remember information about their training data. Through a comprehensive privacy analysis of distributed federated learning models, we design an attack model based on generative adversarial networks (GAN) and member inference attacks (MIA). Malicious participants (attackers) utilize the attack model to successfully reconstruct training sets of other regular participants without any negative impact on the global model. To solve this problem, we apply the differential privacy method to the trai

APA, Harvard, Vancouver, ISO, and other styles

30

Gao, Junyao, Xinyang Jiang, Huishuai Zhang, et al. "Similarity Distribution Based Membership Inference Attack on Person Re-identification." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 12 (2023): 14820–28. http://dx.doi.org/10.1609/aaai.v37i12.26731.

Full text

Abstract:

While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training data. Thus, this paper focuses on quantifying this risk by membership inference (MI) attack. Most of the existing MI attack algorithms focus on classification models, while Re-ID follows a totally different training and inference paradigm. Re-ID is a fine-grained recognition task with complex feature embedding, and model outputs commonly used by existing MI like logits and losses are not accessible during inference. Sin

APA, Harvard, Vancouver, ISO, and other styles

31

Wei, Yuecen, Xingcheng Fu, Lingyun Liu, Qingyun Sun, Hao Peng, and Chunming Hu. "Prompt-based Unifying Inference Attack on Graph Neural Networks." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 12 (2025): 12836–44. https://doi.org/10.1609/aaai.v39i12.33400.

Full text

Abstract:

Graph neural networks (GNNs) provide important prospective insights in applications such as social behavior analysis and financial risk analysis based on their powerful learning capabilities on graph data. Nevertheless, GNNs' predictive performance relies on the quality of task-specific node labels, so it is common practice to improve the model's generalization ability in the downstream execution of decision-making tasks through pre-training. Graph prompting is a prudent choice but risky without taking measures to prevent data leakage. In other words, in high-risk decision scenarios, prompt le

APA, Harvard, Vancouver, ISO, and other styles

32

Cai, Jingyong, Masashi Takemoto, Yuming Qiu, and Hironori Nakajo. "Trigonometric Inference Providing Learning in Deep Neural Networks." Applied Sciences 11, no. 15 (2021): 6704. http://dx.doi.org/10.3390/app11156704.

Full text

Abstract:

Despite being heavily used in the training of deep neural networks (DNNs), multipliers are resource-intensive and insufficient in many different scenarios. Previous discoveries have revealed the superiority when activation functions, such as the sigmoid, are calculated by shift-and-add operations, although they fail to remove multiplications in training altogether. In this paper, we propose an innovative approach that can convert all multiplications in the forward and backward inferences of DNNs into shift-and-add operations. Because the model parameters and backpropagated errors of a large DN

APA, Harvard, Vancouver, ISO, and other styles

33

Yang, Jiayi, Lei Deng, Yukuan Yang, Yuan Xie, and Guoqi Li. "Training and inference for integer-based semantic segmentation network." Neurocomputing 454 (September 2021): 101–12. http://dx.doi.org/10.1016/j.neucom.2021.04.119.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Yu, Shimeng, Wonbo Shim, Xiaochen Peng, and Yandong Luo. "RRAM for Compute-in-Memory: From Inference to Training." IEEE Transactions on Circuits and Systems I: Regular Papers 68, no. 7 (2021): 2753–65. http://dx.doi.org/10.1109/tcsi.2021.3072200.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Dewitz, Peter, Eileen M. Carr, and Judythe P. Patberg. "Effects of Inference Training on Comprehension and Comprehension Monitoring." Reading Research Quarterly 22, no. 1 (1987): 99. http://dx.doi.org/10.2307/747723.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Yuill, Nicola, and Jane Oakhill. "Effects of inference awareness training on poor reading comprehension." Applied Cognitive Psychology 2, no. 1 (1988): 33–45. http://dx.doi.org/10.1002/acp.2350020105.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Bussotti, Jean-Flavien, Enzo Veltri, Donatello Santoro, and Paolo Papotti. "Generation of Training Examples for Tabular Natural Language Inference." Proceedings of the ACM on Management of Data 1, no. 4 (2023): 1–27. http://dx.doi.org/10.1145/3626730.

Full text

Abstract:

Tabular data is becoming increasingly important in Natural Language Processing (NLP) tasks, such as Tabular Natural Language Inference (TNLI). Given a table and a hypothesis expressed in NL text, the goal is to assess if the former structured data supports or refutes the latter. In this work, we focus on the role played by the annotated data in training the inference model. We introduce a system, Tenet, for the automatic augmentation and generation of training examples for TNLI. Given the tables, existing approaches are either based on human annotators, and thus expensive, or on methods that p

APA, Harvard, Vancouver, ISO, and other styles

38

Hilprecht, Benjamin, Martin Härterich, and Daniel Bernau. "Monte Carlo and Reconstruction Membership Inference Attacks against Generative Models." Proceedings on Privacy Enhancing Technologies 2019, no. 4 (2019): 232–49. http://dx.doi.org/10.2478/popets-2019-0067.

Full text

Abstract:

Abstract We present two information leakage attacks that outperform previous work on membership inference against generative models. The first attack allows membership inference without assumptions on the type of the generative model. Contrary to previous evaluation metrics for generative models, like Kernel Density Estimation, it only considers samples of the model which are close to training data records. The second attack specifically targets Variational Autoencoders, achieving high membership inference accuracy. Furthermore, previous work mostly considers membership inference adversaries w

APA, Harvard, Vancouver, ISO, and other styles

39

Hayes, Jamie, Luca Melis, George Danezis, and Emiliano De Cristofaro. "LOGAN: Membership Inference Attacks Against Generative Models." Proceedings on Privacy Enhancing Technologies 2019, no. 1 (2019): 133–52. http://dx.doi.org/10.2478/popets-2019-0008.

Full text

Abstract:

Abstract Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data point, the adversary determines whether or not it was used to train the model. Our attacks leverage Generative Adversarial Networks (GANs), which combine a discriminative and a generative model, to detect overfitting and recognize inputs that were part of training datasets, using the discriminator’s capacity to learn statistical differences in distributi

APA, Harvard, Vancouver, ISO, and other styles

40

Mengu, Deniz, Yifan Zhao, Nezih T. Yardimci, Yair Rivenson, Mona Jarrahi, and Aydogan Ozcan. "Misalignment resilient diffractive optical networks." Nanophotonics 9, no. 13 (2020): 4207–19. http://dx.doi.org/10.1515/nanoph-2020-0291.

Full text

Abstract:

AbstractAs an optical machine learning framework, Diffractive Deep Neural Networks (D2NN) take advantage of data-driven training methods used in deep learning to devise light–matter interaction in 3D for performing a desired statistical inference task. Multi-layer optical object recognition platforms designed with this diffractive framework have been shown to generalize to unseen image data achieving, e.g., >98% blind inference accuracy for hand-written digit classification. The multi-layer structure of diffractive networks offers significant advantages in terms of their diffraction efficie

APA, Harvard, Vancouver, ISO, and other styles

41

Nygaard, Andreas, Emil Brinch Holm, Steen Hannestad, and Thomas Tram. "CONNECT: a neural network based framework for emulating cosmological observables and cosmological parameter inference." Journal of Cosmology and Astroparticle Physics 2023, no. 05 (2023): 025. http://dx.doi.org/10.1088/1475-7516/2023/05/025.

Full text

Abstract:

Abstract Bayesian parameter inference is an essential tool in modern cosmology, and typically requires the calculation of 105–106 theoretical models for each inference of model parameters for a given dataset combination. Computing these models by solving the linearised Einstein-Boltzmann system usually takes tens of CPU core-seconds per model, making the entire process very computationally expensive. In this paper we present connect, a neural network framework emulating class computations as an easy-to-use plug-in for the popular sampler MontePython. connect uses an iteratively trained neural

APA, Harvard, Vancouver, ISO, and other styles

42

Benaissa, Brahim, Masakazu Kobayashi, Keita Kinoshita, and Hiroshi Takenouchi. "A Novel Approach for Individual Design Perception Based on Fuzzy Inference System Training with YUKI Algorithm." Axioms 12, no. 10 (2023): 904. http://dx.doi.org/10.3390/axioms12100904.

Full text

Abstract:

This paper presents a novel approach for individual design perception modeling using the YUKI algorithm-trained Fuzzy Inference System. The study focuses on understanding how individuals perceive design based on personality traits, particularly openness to experience, using the YUKI algorithm and Fuzzy C-means clustering algorithm. The approach generates several Sugeno-type Fuzzy Inference System models to predict design perception, to minimize the Root Mean Squared Error between the model prediction and the actual design perception of participants. The results demonstrate that the suggested m

APA, Harvard, Vancouver, ISO, and other styles

43

Lu, You, Zhiyuan Liu, and Bert Huang. "Block Belief Propagation for Parameter Learning in Markov Random Fields." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 4448–55. http://dx.doi.org/10.1609/aaai.v33i01.33014448.

Full text

Abstract:

Traditional learning methods for training Markov random fields require doing inference over all variables to compute the likelihood gradient. The iteration complexity for those methods therefore scales with the size of the graphical models. In this paper, we propose block belief propagation learning (BBPL), which uses block-coordinate updates of approximate marginals to compute approximate gradients, removing the need to compute inference on the entire graphical model. Thus, the iteration complexity of BBPL does not scale with the size of the graphs. We prove that the method converges to the s

APA, Harvard, Vancouver, ISO, and other styles

44

Li, Tianling, Bin He, and Yangyang Zheng. "Research and Implementation of High Computational Power for Training and Inference of Convolutional Neural Networks." Applied Sciences 13, no. 2 (2023): 1003. http://dx.doi.org/10.3390/app13021003.

Full text

Abstract:

Algorithms and computing power have consistently been the two driving forces behind the development of artificial intelligence. The computational power of a platform has a significant impact on the implementation cost, performance, power consumption, and flexibility of an algorithm. Currently, AI algorithmic models are mainly trained using high-performance GPU platforms, and their inferencing can be implemented using GPU, CPU, and FPGA. On the one hand, due to its high-power consumption and extreme cost, GPU is not suitable for power and cost-sensitive application scenarios. On the other hand,

APA, Harvard, Vancouver, ISO, and other styles

45

Nadendla, Satish Kumar. "Optimizing Real-Time AI Inference with AWS SageMaker and AWS Lambda for Large-Scale Business Applications." International Journal for Research in Applied Science and Engineering Technology 13, no. 4 (2025): 4117–24. https://doi.org/10.22214/ijraset.2025.69100.

Full text

Abstract:

Due to high performance and scalability requirements the real-time AI inference needed in today's massive business applications is simply vital. The author goes on to depict how he successfully improves the use of AWS SageMaker (Amazon Web Services managed service for building, training, and deploying machine learning models) in both model training and deployment by employing AWS Lambda (an event-driven serverless computing platform). With this method businesses can now achieve AI inference at a low cost and with low latency. The main direction is implementing such AWS' AI services as Transcri

APA, Harvard, Vancouver, ISO, and other styles

46

Hu, Wenyang, Xiaocong Cai, Jun Hou, Shuai Yi, and Zhiping Lin. "GTC: Guided Training of CTC towards Efficient and Accurate Scene Text Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (2020): 11005–12. http://dx.doi.org/10.1609/aaai.v34i07.6735.

Full text

Abstract:

Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower accuracy. To design an efficient and effective model, we propose the guided training of CTC (GTC), where CTC model learns a better alignment and feature representations from a more powerful attentional guidance. With the benefit of guided training, CTC model achieves robust and accurate prediction for both regular and irregular scene text while maintaining a fast

APA, Harvard, Vancouver, ISO, and other styles

47

Lee, Ke-Jing, Yu-Chuan Weng, Li-Wen Wang, et al. "High Linearity Synaptic Devices Using Ar Plasma Treatment on HfO2 Thin Film with Non-Identical Pulse Waveforms." Nanomaterials 12, no. 18 (2022): 3252. http://dx.doi.org/10.3390/nano12183252.

Full text

Abstract:

We enhanced the device uniformity for reliable memory performances by increasing the device surface roughness by exposing the HfO2 thin film surface to argon (Ar) plasma. The results showed significant improvements in electrical and synaptic properties, including memory window, linearity, pattern recognition accuracy, and synaptic weight modulations. Furthermore, we proposed a non-identical pulse waveform for further improvement in linearity accuracy. From the simulation results, the Ar plasma processing device using the designed waveform as the input signals significantly improved the off-chi

APA, Harvard, Vancouver, ISO, and other styles

48

Wagh, Sameer, Divya Gupta, and Nishanth Chandran. "SecureNN: 3-Party Secure Computation for Neural Network Training." Proceedings on Privacy Enhancing Technologies 2019, no. 3 (2019): 26–49. http://dx.doi.org/10.2478/popets-2019-0035.

Full text

Abstract:

Abstract Neural Networks (NN) provide a powerful method for machine learning training and inference. To effectively train, it is desirable for multiple parties to combine their data – however, doing so conflicts with data privacy. In this work, we provide novel three-party secure computation protocols for various NN building blocks such as matrix multiplication, convolutions, Rectified Linear Units, Maxpool, normalization and so on. This enables us to construct three-party secure protocols for training and inference of several NN architectures such that no single party learns any information a

APA, Harvard, Vancouver, ISO, and other styles

49

Velikanova, A. S., K. A. Polshchykov, R. V. Likhosherstov, and A. K. Polshchykova. "The use of virtual reality and fuzzy neural network tools to identify the focus on achieving project results." Journal of Physics: Conference Series 2060, no. 1 (2021): 012017. http://dx.doi.org/10.1088/1742-6596/2060/1/012017.

Full text

Abstract:

Abstract In the process of making a decision on the inclusion of an applicant in the project team, it is proposed to take into account his project results targeting (PRT). The article describes the conceptual basis for identifying people’s focus on achieving the results of significant projects based on the use of virtual reality tools and the capabilities of fuzzy inference systems. At the same time, to configure the parameters of the membership functions of the fuzzy inference system and the values of the individual inferences of the fuzzy rules, the use of a neural-fuzzy network is proposed.

APA, Harvard, Vancouver, ISO, and other styles

50

Daniels, Carter W., Jennifer R. Laude, and Thomas R. Zentall. "Six-term transitive inference with pigeons: Successive-pair training followed by mixed-pair training." Journal of the Experimental Analysis of Behavior 101, no. 1 (2013): 26–37. http://dx.doi.org/10.1002/jeab.65.

Full text

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!