Log in

Relevant bibliographies by topics / Regularization by architecture / Journal articles

To see the other types of publications on this topic, follow the link: Regularization by architecture.

Journal articles on the topic 'Regularization by architecture'

Author: Grafiati

Published: 4 June 2025

Last updated: 1 August 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 'Regularization by architecture.'

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

Salehin, Imrus, and Dae-Ki Kang. "A Review on Dropout Regularization Approaches for Deep Neural Networks within the Scholarly Domain." Electronics 12, no. 14 (2023): 3106. http://dx.doi.org/10.3390/electronics12143106.

Full text

Abstract:

Dropout is one of the most popular regularization methods in the scholarly domain for preventing a neural network model from overfitting in the training phase. Developing an effective dropout regularization technique that complies with the model architecture is crucial in deep learning-related tasks because various neural network architectures have been proposed, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), and they have exhibited reasonable performance in their specialized areas. In this paper, we provide a comprehensive and novel review of the state-of

APA, Harvard, Vancouver, ISO, and other styles

2

Marin, Ivana, Ana Kuzmanic Skelin, and Tamara Grujic. "Empirical Evaluation of the Effect of Optimization and Regularization Techniques on the Generalization Performance of Deep Convolutional Neural Network." Applied Sciences 10, no. 21 (2020): 7817. http://dx.doi.org/10.3390/app10217817.

Full text

Abstract:

The main goal of any classification or regression task is to obtain a model that will generalize well on new, previously unseen data. Due to the recent rise of deep learning and many state-of-the-art results obtained with deep models, deep learning architectures have become one of the most used model architectures nowadays. To generalize well, a deep model needs to learn the training data well without overfitting. The latter implies a correlation of deep model optimization and regularization with generalization performance. In this work, we explore the effect of the used optimization algorithm

APA, Harvard, Vancouver, ISO, and other styles

3

Kobayashi, Haruo, Takashi Matsumoto, Tetsuya Yagi, and Takuji Shimmi. "Image processing regularization filters on layered architecture." Neural Networks 6, no. 3 (1993): 327–50. http://dx.doi.org/10.1016/0893-6080(93)90002-e.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Karageorgos, Konstantinos, Anastasios Dimou, Federico Alvarez, and Petros Daras. "Implicit and Explicit Regularization for Optical Flow Estimation." Sensors 20, no. 14 (2020): 3855. http://dx.doi.org/10.3390/s20143855.

Full text

Abstract:

In this paper, two novel and practical regularizing methods are proposed to improve existing neural network architectures for monocular optical flow estimation. The proposed methods aim to alleviate deficiencies of current methods, such as flow leakage across objects and motion consistency within rigid objects, by exploiting contextual information. More specifically, the first regularization method utilizes semantic information during the training process to explicitly regularize the produced optical flow field. The novelty of this method lies in the use of semantic segmentation masks to teach

APA, Harvard, Vancouver, ISO, and other styles

5

Yulita, Winda, Uri Arta Ramadhani, Zunanik Mufidah, et al. "Improved human image density detection with comparison of YOLOv8 depth level architecture and drop-out implementation." Journal of Soft Computing Exploration 6, no. 1 (2025): 33–39. https://doi.org/10.52465/joscex.v6i1.556.

Full text

Abstract:

Energy inefficiency due to Air Conditioners (AC) running in empty rooms contribute to unnecessary energy consumption and increased CO₂ emissions. This study explores how different depth levels of the YOLOv8 architecture and dropout regularization can enhance human density detection for smarter AC control systems. By evaluating model accuracy through Mean Average Precision (mAP50-95), we provide quantitative insights into how these modifications improve detection performance. Our dataset consists of 1363 images taken in an office environment at ITERA under varying lighting conditions and differ

APA, Harvard, Vancouver, ISO, and other styles

6

Glänzer, Lukas, Husam E. Masalkhi, Anjali A. Roeth, Thomas Schmitz-Rode, and Ioana Slabu. "Vessel Delineation Using U-Net: A Sparse Labeled Deep Learning Approach for Semantic Segmentation of Histological Images." Cancers 15, no. 15 (2023): 3773. http://dx.doi.org/10.3390/cancers15153773.

Full text

Abstract:

Semantic segmentation is an important imaging analysis method enabling the identification of tissue structures. Histological image segmentation is particularly challenging, having large structural information while providing only limited training data. Additionally, labeling these structures to generate training data is time consuming. Here, we demonstrate the feasibility of a semantic segmentation using U-Net with a novel sparse labeling technique. The basic U-Net architecture was extended by attention gates, residual and recurrent links, and dropout regularization. To overcome the high class

APA, Harvard, Vancouver, ISO, and other styles

7

Zhang, Jiang, Liejun Wang, Yinfeng Yu, and Miaomiao Xu. "Nonlinear Regularization Decoding Method for Speech Recognition." Sensors 24, no. 12 (2024): 3846. http://dx.doi.org/10.3390/s24123846.

Full text

Abstract:

Existing end-to-end speech recognition methods typically employ hybrid decoders based on CTC and Transformer. However, the issue of error accumulation in these hybrid decoders hinders further improvements in accuracy. Additionally, most existing models are built upon Transformer architecture, which tends to be complex and unfriendly to small datasets. Hence, we propose a Nonlinear Regularization Decoding Method for Speech Recognition. Firstly, we introduce the nonlinear Transformer decoder, breaking away from traditional left-to-right or right-to-left decoding orders and enabling associations

APA, Harvard, Vancouver, ISO, and other styles

8

Bhatt, Dulari, Chirag Patel, Hardik Talsania, et al. "CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope." Electronics 10, no. 20 (2021): 2470. http://dx.doi.org/10.3390/electronics10202470.

Full text

Abstract:

Computer vision is becoming an increasingly trendy word in the area of image processing. With the emergence of computer vision applications, there is a significant demand to recognize objects automatically. Deep CNN (convolution neural network) has benefited the computer vision community by producing excellent results in video processing, object recognition, picture classification and segmentation, natural language processing, speech recognition, and many other fields. Furthermore, the introduction of large amounts of data and readily available hardware has opened new avenues for CNN study. Se

APA, Harvard, Vancouver, ISO, and other styles

9

Bevza, M. "Tying of embeddings for improving regularization in neural networks for named entity recognition task." Bulletin of Taras Shevchenko National University of Kyiv. Series: Physics and Mathematics, no. 3 (2018): 59–64. http://dx.doi.org/10.17721/1812-5409.2018/3.8.

Full text

Abstract:

We analyze neural network architectures that yield state of the art results on named entity recognition task and propose a new architecture for improving results even further. We have analyzed a number of ideas and approaches that researchers have used to achieve state of the art results in a variety of NLP tasks. In this work, we present a few of them which we consider to be most likely to improve existing state of the art solutions for named entity recognition task. The architecture is inspired by recent developments in language modeling task. The suggested solution is based on a multi-task

APA, Harvard, Vancouver, ISO, and other styles

10

Albahar, Marwan Ali, and Muhammad Binsawad. "Deep Autoencoders and Feedforward Networks Based on a New Regularization for Anomaly Detection." Security and Communication Networks 2020 (July 10, 2020): 1–9. http://dx.doi.org/10.1155/2020/7086367.

Full text

Abstract:

Anomaly detection is a problem with roots dating back over 30 years. The NSL-KDD dataset has become the convention for testing and comparing new or improved models in this domain. In the field of network intrusion detection, the UNSW-NB15 dataset has recently gained significant attention over the NSL-KDD because it contains more modern attacks. In the present paper, we outline two cutting-edge architectures that push the boundaries of model accuracy for these datasets, both framed in the context of anomaly detection and intrusion classification. We summarize training methodologies, hyperparame

APA, Harvard, Vancouver, ISO, and other styles

11

Li, Jianming, Changchang Zeng, Min Zhou, Zeyi Shang, and Jiangang Zhu. "Chromosome Image Classification Based on Improved Differentiable Architecture Search." Electronics 14, no. 9 (2025): 1820. https://doi.org/10.3390/electronics14091820.

Full text

Abstract:

Chromosomes are essential carriers of human genetic material, and karyotype diagnosis plays a crucial role in prenatal diagnostics, genetic disease identification, and medical research. Physicians rely heavily on karyotype images to diagnose potential abnormalities in chromosome numbers and structure. However, the process is tedious and challenging. To improve diagnostic efficiency and accuracy, artificial intelligence (AI) researchers have developed convolutional neural networks (CNNs) for chromosome image classification. Despite this progress, the gap between cytogeneticists and AI experts r

APA, Harvard, Vancouver, ISO, and other styles

12

Liu, Yingru, Xuewen Yang, Dongliang Xie, et al. "Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 4924–31. http://dx.doi.org/10.1609/aaai.v34i04.5930.

Full text

Abstract:

Multi-task learning (MTL) is a common paradigm that seeks to improve the generalization performance of task learning by training related tasks simultaneously. However, it is still a challenging problem to search the flexible and accurate architecture that can be shared among multiple tasks. In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL. The main principle of TAAN is to derive flexible activation functions for different tasks from the data with other parameters of the net

APA, Harvard, Vancouver, ISO, and other styles

13

Kamble, Yogesh M., and Raj B. Kulkarni. "Recommendation System for Hairstyle Based on Face Recognition Using AI and Machine Learning." International Journal of Software Innovation 12, no. 1 (2024): 1–10. http://dx.doi.org/10.4018/ijsi.309960.

Full text

Abstract:

Many machine learning algorithms have been introduced to solve different types of problems. Recently, many of these algorithms have been applied to deep architecture models and showed very impressive performances. In general, deep architecture models suffer from the over-fitting problem when there is a small number of training data. In this article the attempt is made to remedy this problem in deep architecture with regularization techniques including overlap pooling and flipped image augmentation and dropout; the authors also compared a deep structure model (convolutional neural network (CNN)

APA, Harvard, Vancouver, ISO, and other styles

14

Dittmer, Sören, Tobias Kluth, Peter Maass, and Daniel Otero Baguer. "Regularization by Architecture: A Deep Prior Approach for Inverse Problems." Journal of Mathematical Imaging and Vision 62, no. 3 (2019): 456–70. http://dx.doi.org/10.1007/s10851-019-00923-x.

Full text

Abstract:

Abstract The present paper studies so-called deep image prior (DIP) techniques in the context of ill-posed inverse problems. DIP networks have been recently introduced for applications in image processing; also first experimental results for applying DIP to inverse problems have been reported. This paper aims at discussing different interpretations of DIP and to obtain analytic results for specific network designs and linear operators. The main contribution is to introduce the idea of viewing these approaches as the optimization of Tikhonov functionals rather than optimizing networks. Besides

APA, Harvard, Vancouver, ISO, and other styles

15

Dittmer, Sören, Tobias Kluth, Peter Maass, and Baguer Daniel Otero. "Regularization by Architecture: A Deep Prior Approach for Inverse Problems." Journal of Mathematical Imaging and Vision 62 (October 30, 2019): 456–70. https://doi.org/10.1007/s10851-019-00923-x.

Full text

Abstract:

The present paper studies so-called deep image prior (DIP) techniques in the context of ill-posed inverse problems. DIP networks have been recently introduced for applications in image processing; also first experimental results for applyingDIP to inverse problems have been reported. This paper aims at discussing different interpretations of DIP and to obtain analytic results for specific network designs and linear operators. The main contribution is to introduce the idea of viewing these approaches as the optimization of Tikhonov functionals rather than optimizing networks. Besides theoretica

APA, Harvard, Vancouver, ISO, and other styles

16

Ding, Xiaohui, Yong Li, Ji Yang, et al. "An Adaptive Capsule Network for Hyperspectral Remote Sensing Classification." Remote Sensing 13, no. 13 (2021): 2445. http://dx.doi.org/10.3390/rs13132445.

Full text

Abstract:

The capsule network (Caps) is a novel type of neural network that has great potential for the classification of hyperspectral remote sensing. However, the Caps suffers from the issue of gradient vanishing. To solve this problem, a powered activation regularization based adaptive capsule network (PAR-ACaps) was proposed for hyperspectral remote sensing classification, in which an adaptive routing algorithm without iteration was applied to amplify the gradient, and the powered activation regularization method was used to learn the sparser and more discriminative representation. The classificatio

APA, Harvard, Vancouver, ISO, and other styles

17

Oliveros-Oliveros, José Jacobo, José Rubén Conde-Sánchez, Carlos Arturo Hernández-Gracidas, María Monserrat Morín-Castillo, and José Julio Conde-Mones. "FPGA-Based Hardware Implementation of a Stable Inverse Source Problem Algorithm in a Non-Homogeneous Circular Region." Applied Sciences 14, no. 4 (2024): 1388. http://dx.doi.org/10.3390/app14041388.

Full text

Abstract:

Objective: This work presents an implementation of a stable algorithm that recovers sources located at the boundary separating two homogeneous media in field-programmable gate arrays. Two loop unrolling architectures were developed and analyzed for this purpose. This inverse source problem is ill-posed due to numerical instability, i.e., small errors in the measurement can produce significant changes in the source location. Methodology: To handle the numerical instability when recovering these sources, the Tikhonov regularization method in combination with the Fourier series truncation method

APA, Harvard, Vancouver, ISO, and other styles

18

Patel,, Neha. "AI-Personalized Elegance: Optimizing Your Appearance with Smart Hairstyle Recommendations." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 06 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem36150.

Full text

Abstract:

Many machine learning algorithms have been introduced to solve different types of problems. Recently, many of these algorithms have been applied to deep architecture models and showed very impressive performances. In general, deep architecture models suffer from the over-fitting problem when there is a small number of training data. In this article the attempt is made to remedy this problem in deep architecture with regularization techniques including overlap pooling and flipped image augmentation and dropout; the authors also compared a deep structure model (convolutional neural network (CNN)

APA, Harvard, Vancouver, ISO, and other styles

19

Yan, Songcai, Xinjun Hu, and Qinyuan Xue. "Dual Task Semi-supervised Pancreatic Segmentation Based on Prior Information and Multiple Regularization." Mathematical Modeling and Algorithm Application 2, no. 1 (2024): 11–19. http://dx.doi.org/10.54097/p6445f38.

Full text

Abstract:

Due to the relatively small size and complex internal structure of the pancreas, the segmentation is often inaccurate during image processing. A more effective automatic segmentation method is proposed to solve this problem. A multi-task deep neural network architecture based on V-Net architecture is proposed. By capturing the relationship between the prior positions of the pancreas, the target of the pancreas can be constrained at the regional level. In addition, this study uses dual task training methods to simultaneously perform segmentation tasks and regression tasks, and generate high-qua

APA, Harvard, Vancouver, ISO, and other styles

20

Ridho, Akhmad, and Alamsyah Alamsyah. "Chaotic Whale Optimization Algorithm in Hyperparameter Selection in Convolutional Neural Network Algorithm." Journal of Advances in Information Systems and Technology 4, no. 2 (2023): 156–69. http://dx.doi.org/10.15294/jaist.v4i2.60595.

Full text

Abstract:

In several previous studies, metaheuristic methods were used to search for CNN hyperparameters. However, this research only focuses on searching for CNN hyperparameters in the type of network architecture, network structure, and initializing network weights. Therefore, in this article, we only focus on searching for CNN hyperparameters with network architecture type, and network structure with additional regularization. In this article, the CNN hyperparameter search with regularization uses CWOA on the MNIST and FashionMNIST datasets. Each dataset consists of 60,000 training data and 10,000 te

APA, Harvard, Vancouver, ISO, and other styles

21

Shi, Jialin, Chenyi Guo, and Ji Wu. "A Hybrid Robust-Learning Architecture for Medical Image Segmentation with Noisy Labels." Future Internet 14, no. 2 (2022): 41. http://dx.doi.org/10.3390/fi14020041.

Full text

Abstract:

Deep-learning models require large amounts of accurately labeled data. However, for medical image segmentation, high-quality labels rely on expert experience, and less-experienced operators provide noisy labels. How one might mitigate the negative effects caused by noisy labels for 3D medical image segmentation has not been fully investigated. In this paper, our purpose is to propose a novel hybrid robust-learning architecture to combat noisy labels for 3D medical image segmentation. Our method consists of three components. First, we focus on the noisy annotations of slices and propose a slice

APA, Harvard, Vancouver, ISO, and other styles

22

Sewak, Mohit, Sanjay K. Sahay, and Hemant Rathore. "An Overview of Deep Learning Architecture of Deep Neural Networks and Autoencoders." Journal of Computational and Theoretical Nanoscience 17, no. 1 (2020): 182–88. http://dx.doi.org/10.1166/jctn.2020.8648.

Full text

Abstract:

The recent wide applications of deep learning in multiple fields has shown a great progress, but to perform optimally, it requires the adjustment of various architectural features and hyper-parameters. Moreover, deep learning could be used with multiple varieties of architecture aimed at different objectives, e.g., autoencoders are popular for un-supervised learning applications for reducing the dimensionality of the dataset. Similarly, deep neural networks are popular for supervised learning applications viz., classification, regression, etc. Besides the type of deep learning architecture, so

APA, Harvard, Vancouver, ISO, and other styles

23

Farabbi, Andrea, and Luca Mainardi. "Domain-Specific Processing Stage for Estimating Single-Trail Evoked Potential Improves CNN Performance in Detecting Error Potential." Sensors 23, no. 22 (2023): 9049. http://dx.doi.org/10.3390/s23229049.

Full text

Abstract:

We present a novel architecture designed to enhance the detection of Error Potential (ErrP) signals during ErrP stimulation tasks. In the context of predicting ErrP presence, conventional Convolutional Neural Networks (CNNs) typically accept a raw EEG signal as input, encompassing both the information associated with the evoked potential and the background activity, which can potentially diminish predictive accuracy. Our approach involves advanced Single-Trial (ST) ErrP enhancement techniques for processing raw EEG signals in the initial stage, followed by CNNs for discerning between ErrP and

APA, Harvard, Vancouver, ISO, and other styles

24

Guo, Ao. "Enhancing Facial Expression Recognition with Robust CNN Architectures and Adaptive Preprocessing Techniques." Applied and Computational Engineering 100, no. 1 (2025): None. https://doi.org/10.54254/2755-2721/2025.20426.

Full text

Abstract:

Facial expression recognition (FER) is an essential technology at the intersection of artificial intelligence (AI), computer vision, and psychology. This study proposes a novel framework for FER, aiming to improve system robustness and generalization, especially under variable real-world conditions. Using the FER2013 dataset, this research combines an adaptive preprocessing pipeline with a custom Convolutional Neural Network (CNN) architecture. Key preprocessing steps include normalization, rotation, and flipping to improve data quality and diversity. The CNN architecture combines regularizati

APA, Harvard, Vancouver, ISO, and other styles

25

Sudhakar, Sengan, P. Kanmani, K. Amudha, et al. "Network embedding architecture using laplace regularization-non-negative matrix factorization for virtualization." Microprocessors and Microsystems 81 (March 2021): 103616. http://dx.doi.org/10.1016/j.micpro.2020.103616.

Full text

APA, Harvard, Vancouver, ISO, and other styles

26

Sen, Satyakee, Sribharath Kainkaryam, Cen Ong, and Arvind Sharma. "Regularization strategies for deep-learning-based salt model building." Interpretation 7, no. 4 (2019): T911—T922. http://dx.doi.org/10.1190/int-2018-0229.1.

Full text

Abstract:

Salt model building has long been considered a severe bottleneck for large-scale 3D seismic imaging projects. It is one of the most time-consuming, labor-intensive, and difficult-to-automate processes in the entire depth imaging workflow requiring significant intervention by domain experts to manually interpret the salt bodies on noisy, low-frequency, and low-resolution seismic images at each iteration of the salt model building process. The difficulty and need for automating this task is well-recognized by the imaging community and has propelled the use of deep-learning-based convolutional ne

APA, Harvard, Vancouver, ISO, and other styles

27

Miyajima, Koji, Naoki Mukawa, and Mamoru Okada. "Regularization using the MDL principle: estimation of regularization parameters for regions containing discontinuities." Systems and Computers in Japan 30, no. 8 (1999): 61–71. http://dx.doi.org/10.1002/(sici)1520-684x(199907)30:8<61::aid-scj7>3.0.co;2-j.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Benavente, David, Gustavo Gatica, and Jesús González-Feliu. "Balanced Medical Image Classification with Transfer Learning and Convolutional Neural Networks." Axioms 11, no. 3 (2022): 115. http://dx.doi.org/10.3390/axioms11030115.

Full text

Abstract:

This paper aims to propose a tool for image classification in medical diagnosis decision support, in a context where computational power is limited and then specific, high-speed computing infrastructures cannot be used (mainly for economic and energy consuming reasons). The proposed method combines a deep neural networks algorithm with medical imaging procedures and is implemented to allow an efficient use on affordable hardware. The convolutional neural network (CNN) procedure used VGG16 as its base architecture, using the transfer learning technique with the parameters obtained in the ImageN

APA, Harvard, Vancouver, ISO, and other styles

29

Zhou, Yuchen. "Music Generation Based on Bidirectional GRU Model." Highlights in Science, Engineering and Technology 85 (March 13, 2024): 684–90. http://dx.doi.org/10.54097/t2szjs78.

Full text

Abstract:

Lately, substantial advancements in the realm of deep learning have given rise to new approaches for autonomously generating music. This study has devised a generative framework intended to produce musical melodies. This framework capitalizes on bidirectional gated recurrent units (GRU) as its foundational architecture. To impart knowledge to the model, a collection of classical piano compositions in MIDI format has been employed as the training dataset. One implements a stacked architecture of bidirectional GRU layers to capture long-term musical patterns. The addition of dropout regularizati

APA, Harvard, Vancouver, ISO, and other styles

30

Schröder, Dominik, Hugo Cui, Daniil Dmitriev, and Bruno Loureiro. "Deterministic equivalent and error universality of deep random features learning^*." Journal of Statistical Mechanics: Theory and Experiment 2024, no. 10 (2024): 104017. http://dx.doi.org/10.1088/1742-5468/ad65e2.

Full text

Abstract:

Abstract This manuscript considers the problem of learning a random Gaussian network function using a fully connected network with frozen intermediate layers and trainable readout layer. This problem can be seen as a natural generalization of the widely studied random features model to deeper architectures. First, we prove Gaussian universality of the test error in a ridge regression setting where the learner and target networks share the same intermediate layers, and provide a sharp asymptotic formula for it. Establishing this result requires proving a deterministic equivalent for traces of t

APA, Harvard, Vancouver, ISO, and other styles

31

Kuklin, Vladimir Zh, Aslan A. Tatarkanov, and Alexander A. Umyskov. "Trainable Regularization in Dense Image Matching Problems." HighTech and Innovation Journal 4, no. 3 (2023): 617–29. http://dx.doi.org/10.28991/hij-2023-04-03-011.

Full text

Abstract:

This study examines the development of specialized models designed to solve image-matching problems. The purpose of this research is to develop a technique based on energy tensor aggregation for dense image matching. This task is relevant within the framework of computer systems since image comparison makes it possible to solve current problems such as reconstructing a three-dimensional model of an object, creating a panorama scene, ensuring object recognition, etc. This paper examines in detail the key features of the image matching process based on the use of binocular stereo reconstruction

APA, Harvard, Vancouver, ISO, and other styles

32

Saraswati, Ni Wayan Sumartini, I. Wayan Dharma Suryawan, Ni Komang Tri Juniartini, I. Dewa Made Krishna Muku, Poria Pirozmand, and Weizhi Song. "Recognizing Pneumonia Infection in Chest X-Ray Using Deep Learning." MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer 23, no. 1 (2023): 17–28. http://dx.doi.org/10.30812/matrik.v23i1.3197.

Full text

Abstract:

One of the diseases that attacks the lungs is pneumonia. Pneumonia is inflammation and fluid in the lungs making it difficult to breathe. This disease is diagnosed using X-Ray. Against the darker background of the lungs, infected tissue shows denser areas, which causes them to appear as white spots called infiltrates. In the image processing approach, pneumonia-infected X-rays can be detected using machine learning as well as deep learning. The convolutional neural network model is able to recognize images well and focus on points that are invisible to the human eye. Previous research using a

APA, Harvard, Vancouver, ISO, and other styles

33

Raj, Ashish, Christopher Hess, and Pratik Mukherjee. "Spatial HARDI: Improved visualization of complex white matter architecture with Bayesian spatial regularization." NeuroImage 54, no. 1 (2011): 396–409. http://dx.doi.org/10.1016/j.neuroimage.2010.07.040.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Jethva, Rishi. "CNN Module on MNIST Dataset for Written Digit Classification." International Journal for Research in Applied Science and Engineering Technology 12, no. 3 (2024): 3387–89. http://dx.doi.org/10.22214/ijraset.2024.59419.

Full text

Abstract:

Abstract: Convolutional Neural Networks (CNNs) have become indispensable tools in the realm of image classification, particularly in tasks like handwritten digit recognition. In this comprehensive study, we delve into the intricate world of CNN modules as applied to the MNIST dataset, a cornerstone benchmark in machine learning. Our research aims to meticulously assess the performance of diverse CNN architectures, encompassing variations in depth, convolutional layer configurations, pooling strategies, and regularization techniques. Through exhaustive experimentation and meticulous analysis, w

APA, Harvard, Vancouver, ISO, and other styles

35

Li, Yishi, Kunran Xu, Rui Lai, and Lin Gu. "Towards an Effective Orthogonal Dictionary Convolution Strategy." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 2 (2022): 1473–81. http://dx.doi.org/10.1609/aaai.v36i2.20037.

Full text

Abstract:

Orthogonality regularization has proven effective in improving the precision, convergence speed and the training stability of CNNs. Here, we propose a novel Orthogonal Dictionary Convolution Strategy (ODCS) on CNNs to improve orthogonality effect by optimizing the network architecture and changing the regularized object. Specifically, we remove the nonlinear layer in typical convolution block “Conv(BN) + Nonlinear + Pointwise Conv(BN)”, and only impose orthogonal regularization on the front Conv. The structure, “Conv(BN) + Pointwise Conv(BN)”, is then equivalent to a pair of dictionary and enc

APA, Harvard, Vancouver, ISO, and other styles

36

Emelyanov, Anton, Vladimir Knyaz, Vladimir Kniaz, and Dana Artist. "Pixels relationship analysis for extracting building footprints." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVIII-3-2024 (November 7, 2024): 141–46. http://dx.doi.org/10.5194/isprs-archives-xlviii-3-2024-141-2024.

Full text

Abstract:

Abstract. Currently, remote sensing research is focused on developing an automated algorithm that can compete with empirical methods for mapping the contours of individual buildings. Despite facing numerous challenges related to suboptimal imaging conditions, diverse building architecture, and complex backgrounds, creating such an algorithm is essential for monitoring urban and natural areas, generating 3D city models, managing disasters, and estimating population density. Obtaining the polygonal boundary of a building and extracting a vectorized building mask as output for direct use is one o

APA, Harvard, Vancouver, ISO, and other styles

37

Böckmann, Christine, and Andreas Kirsche. "Iterative regularization method for lidar remote sensing." Computer Physics Communications 174, no. 8 (2006): 607–15. http://dx.doi.org/10.1016/j.cpc.2005.12.019.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Hagad, Juan Lorenzo, Tsukasa Kimura, Ken-ichi Fukui, and Masayuki Numao. "Learning Subject-Generalized Topographical EEG Embeddings Using Deep Variational Autoencoders and Domain-Adversarial Regularization." Sensors 21, no. 5 (2021): 1792. http://dx.doi.org/10.3390/s21051792.

Full text

Abstract:

Two of the biggest challenges in building models for detecting emotions from electroencephalography (EEG) devices are the relatively small amount of labeled samples and the strong variability of signal feature distributions between different subjects. In this study, we propose a context-generalized model that tackles the data constraints and subject variability simultaneously using a deep neural network architecture optimized for normally distributed subject-independent feature embeddings. Variational autoencoders (VAEs) at the input level allow the lower feature layers of the model to be trai

APA, Harvard, Vancouver, ISO, and other styles

39

M, Muniraju, Nagendrababu N. C, Pavani, Ramamani A. N, Varsha S, and Vijayalakshmi K. R. "A Semi Supervised Architecture for Diabetic Retinopathy Diagnosis." International Journal for Research in Applied Science and Engineering Technology 13, no. 3 (2025): 3501–7. https://doi.org/10.22214/ijraset.2025.68027.

Full text

Abstract:

Abstract: Diabetic Retinopathy (DR) is one of the leading causes of blindness worldwide, making its early detection crucial for preventing severe vision loss. Since diabetic retinopathy (DR) is one of the main causes of blindness in the world, it is imperative that it be detected early to avoid serious vision loss. The rising incidence of diabetes necessitates scalable and effective DR diagnosis methods.Largelabeleddatasets,whicharecostlyandtime- consuming to obtain, are frequently needed for DR detectionusingtraditionalsupervised learningtechniques. Inordertoclassifydiabeticretinopathy,thispa

APA, Harvard, Vancouver, ISO, and other styles

40

Ichsan, Aulia, Sugeng Riyadi, and Doughlas Pardede. "Analysis of Logistic Regression Regularization in Wild Elephant Classification with VGG-16 Feature Extraction." Journal of Computer Networks, Architecture and High Performance Computing 6, no. 2 (2024): 783–93. http://dx.doi.org/10.47709/cnahpc.v6i2.3789.

Full text

Abstract:

The research article explores the intersection of image-based wildlife classification and logistic regression regularization, focusing on the classification of wild elephant species. It begins by highlighting the significance of ecological research in biodiversity monitoring and conservation and introduces Convolutional Neural Networks (CNNs) as potent tools for feature extraction from images. The VGG-16 model is particularly emphasized for its ability to capture hierarchical representations of visual features crucial for classification tasks. The integration of VGG-16 feature extraction with

APA, Harvard, Vancouver, ISO, and other styles

41

КАЗІОНОВ, МАКСИМ, ТЕТЯНА СКРИПНИК, ОЛЕКСАНДР ПАСІЧНИК та ЛЕОНІД ВОЗНЮК. "ВДОСКОНАЛЕНИЙ МЕТОД ВИЯВЛЕННЯ БПЛА ЗА ТЕПЛОВІЗІЙНИМИ ЗОБРАЖЕННЯМИ НА ОСНОВІ МОДЕЛІ ГЛИБОКОГО НАВЧАННЯ YOLO". Herald of Khmelnytskyi National University. Technical sciences 347, № 1 (2025): 571–75. https://doi.org/10.31891/2307-5732-2025-347-79.

Full text

Abstract:

This paper presents the results of a study on the detection of UAVs in thermal images using deep learning methods. The primary focus is on the development and improvement of the YOLO architecture, which enables effective detection and localization of UAVs in real time. To train and test the models, the public “shahed136-detect” dataset with 8,100 thermal images was used, along with the simulation of various weather conditions, such as fog, rain, and noise. To enhance the model’s robustness under real operating conditions, several improvements to the YOLO architecture were implemented. These in

APA, Harvard, Vancouver, ISO, and other styles

42

Chen, Ziye, Cheng Ding, Yanghui Rao, et al. "Hierarchical neural topic modeling with manifold regularization." World Wide Web 24, no. 6 (2021): 2139–60. http://dx.doi.org/10.1007/s11280-021-00963-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Kwon, Soondong, Dongyoun Kim, Bongsoo Han, and Kiwoon Kwon. "Regularization of DT-MRI Using 3D Median Filtering Methods." Journal of Applied Mathematics 2014 (2014): 1–11. http://dx.doi.org/10.1155/2014/285367.

Full text

Abstract:

DT-MRI (diffusion tensor magnetic resonance imaging) tractography is a method to determine the architecture of axonal fibers in the central nervous system by computing the direction of the principal eigenvectors obtained from tensor matrix, which is different from the conventional isotropic MRI. Tractography based on DT-MRI is known to need many computations and is highly sensitive to noise. Hence, adequate regularization methods, such as image processing techniques, are in demand. Among many regularization methods we are interested in the median filtering method. In this paper, we extended tw

APA, Harvard, Vancouver, ISO, and other styles

44

Bozorov, Suhrobjon. "OPTIMIZING NEURAL NETWORK ARCHITECTURE FOR ENHANCED ATTACK DETECTION: A COMPREHENSIVE APPROACH." Innovative Development in Educational Activities 2, no. 23 (2023): 62–74. https://doi.org/10.5281/zenodo.10391950.

Full text

Abstract:

<em>In the realm of cybersecurity, robust attack detection mechanisms are imperative due to the increasing sophistication of cyber threats. Machine learning techniques, particularly neural networks, have emerged as powerful tools for identifying and mitigating these attacks. The performance of a neural network heavily relies on its architecture, including features, hidden layers, and hidden neurons. This article explores the intricacies of optimizing neural network architecture to enhance attack detection, drawing from recent research and practical applications. The significance of feature sel

APA, Harvard, Vancouver, ISO, and other styles

45

Ayodele, Bamidele, Siti Mustapa, May Alsaffar, and Chin Cheng. "Artificial Intelligence Modelling Approach for the Prediction of CO-Rich Hydrogen Production Rate from Methane Dry Reforming." Catalysts 9, no. 9 (2019): 738. http://dx.doi.org/10.3390/catal9090738.

Full text

Abstract:

This study investigates the applicability of the Leven–Marquardt algorithm, Bayesian regularization, and a scaled conjugate gradient algorithm as training algorithms for an artificial neural network (ANN) predictively modeling the rate of CO and H2 production by methane dry reforming over a Co/Pr2O3 catalyst. The dataset employed for the ANN modeling was obtained using a central composite experimental design. The input parameters consisted of CH4 partial pressure, CO2 partial pressure, and reaction temperature, while the target parameters included the rate of CO and H2 production. A neural net

APA, Harvard, Vancouver, ISO, and other styles

46

Slutsky, Michael. "Noise-Adaptive Non-Blind Image Deblurring." Sensors 22, no. 18 (2022): 6923. http://dx.doi.org/10.3390/s22186923.

Full text

Abstract:

This work addresses the problem of non-blind image deblurring for arbitrary input noise. The problem arises in the context of sensors with strong chromatic aberrations, as well as in standard cameras, in low-light and high-speed scenarios. A short description of two common classical approaches to regularized image deconvolution is provided, and common issues arising in this context are described. It is shown how a pre-deconvolved deep neural network (DNN) based image enhancement can be improved by joint optimization of regularization parameters and network weights. Furthermore, a two-step appr

APA, Harvard, Vancouver, ISO, and other styles

47

Shaheryar, Ahmad, Xu-Cheng Yin, Hong-Wei Hao, Hazrat Ali, and Khalid Iqbal. "A Denoising Based Autoassociative Model for Robust Sensor Monitoring in Nuclear Power Plants." Science and Technology of Nuclear Installations 2016 (2016): 1–17. http://dx.doi.org/10.1155/2016/9746948.

Full text

Abstract:

Sensors health monitoring is essentially important for reliable functioning of safety-critical chemical and nuclear power plants. Autoassociative neural network (AANN) based empirical sensor models have widely been reported for sensor calibration monitoring. However, such ill-posed data driven models may result in poor generalization and robustness. To address above-mentioned issues, several regularization heuristics such as training with jitter, weight decay, and cross-validation are suggested in literature. Apart from these regularization heuristics, traditional error gradient based supervis

APA, Harvard, Vancouver, ISO, and other styles

48

Sajun, Ali Reza, and Imran Zualkernan. "Survey on Implementations of Generative Adversarial Networks for Semi-Supervised Learning." Applied Sciences 12, no. 3 (2022): 1718. http://dx.doi.org/10.3390/app12031718.

Full text

Abstract:

Given recent advances in deep learning, semi-supervised techniques have seen a rise in interest. Generative adversarial networks (GANs) represent one recent approach to semi-supervised learning (SSL). This paper presents a survey method using GANs for SSL. Previous work in applying GANs to SSL are classified into pseudo-labeling/classification, encoder-based, TripleGAN-based, two GAN, manifold regularization, and stacked discriminator approaches. A quantitative and qualitative analysis of the various approaches is presented. The R3-CGAN architecture is identified as the GAN architecture with s

APA, Harvard, Vancouver, ISO, and other styles

49

Mon, Yi-Jen. "Tikhonov-Tuned Sliding Neural Network Decoupling Control for an Inverted Pendulum." Electronics 12, no. 21 (2023): 4415. http://dx.doi.org/10.3390/electronics12214415.

Full text

Abstract:

This paper introduces the concept of intelligent control using Tikhonov regularization for nonlinear coupled systems. This research is driven by the increasing demand for advanced control techniques and aims to explore the impact of Tikhonov regularization on these systems. The primary objective is to determine the optimal regularization term and its integration with other control methods to enhance intelligent control for nonlinear coupled systems. Tikhonov regularization is a technique employed to adjust neural network weights and prevent overfitting. Additionally, the incorporation of ReLU

APA, Harvard, Vancouver, ISO, and other styles

50

Bing Yang, Junyan Tan, Ling Zhen, and Ling Jing. "Network-Based Gene Sets Selection Via Network Regularization." Journal of Convergence Information Technology 8, no. 4 (2013): 779–88. http://dx.doi.org/10.4156/jcit.vol8.issue4.90.

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!