Search · four archives

Results for batch normalization

or ask it as a questionAsk the stacks →

ArchivesarXiv PubMed bioRxiv chemRxiv

WhenAny time Past month Past year Past 5 years

OrderMost relevant Most cited Newest

12 papers · ranked by Valyu relevance

01
PPubMed6 Nov 2019
Lightweight Convolutional Neural Network and Its Application in Rolling Bearing Fault Diagnosis under Variable Working Conditions
Hengchang Liu, Dechen Yao, Jianwei Yang, Xi Li
The rolling bearing is an important part of the train’s running gear, and its operating state determines the safety during the running of the train. Therefore, it is important to monitor and diagnose the health status of rolling bearings. A convolutional neural network is widely used in the field of fault diagnosis…
92relevance
02
PPubMed9 Dec 2021
Revisiting Batch Normalization for Training Low-Latency Deep Spiking Neural Networks From Scratch
Youngeun Kim, Priyadarshini Panda
Spiking Neural Networks (SNNs) have recently emerged as an alternative to deep learning owing to sparse, asynchronous and binary event (or spike) driven processing, that can yield huge energy efficiency benefits on neuromorphic hardware. However, SNNs convey temporally-varying spike activation through time that is…
90relevance
03
PPubMed17 Feb 2022
CytofIn enables integrated analysis of public mass cytometry datasets using generalized anchors
Yu-Chen Lo, Timothy J. Keyes, Astraea Jager, Jolanda Sarno + 9 more
'Pablo Domizi' 'Ravindra Majeti' 'Kathleen M. Sakamoto' 'Norman Lacayo' 'Charles G. Mullighan' 'Jeffrey Waters' 'Bita Sahaf' 'Sean C. Bendall' 'Kara L. Davis'] The increasing use of mass cytometry for analyzing clinical samples offers the possibility to perform comparative analyses across public datasets. However…
88relevance
04
PPubMed10 Jun 2022
Instance Segmentation Based on Improved Self-Adaptive Normalization
Sen Yang, Xiaobao Wang, Qijuan Yang, Enzeng Dong + 2 more
'Cosimo Distante'] The single batch normalization (BN) method is commonly used in the instance segmentation algorithms. The batch size is concerned with some drawbacks. A too small sample batch size leads to a sharp drop in accuracy, but a too large batch may result in the memory overflow of graphic processing units…
87relevance
05
PPubMed16 Dec 2022
Improving Network Training on Resource-Constrained Devices via Habituation Normalization †
Huixia Lai, Lulu Zhang, Shi Zhang, Antonio Lázaro
As a technique for accelerating and stabilizing training, the batch normalization (BN) is widely used in deep learning. However, BN cannot effectively estimate the mean and the variance of samples when training/fine-tuning with small batches of data on resource-constrained devices. It will lead to a decrease in the…
86relevance
06
PPubMed17 Jun 2025
Attention-Based Batch Normalization for Binary Neural Networks
Shan Gu, Guoyin Zhang, Chengwei Jia, Yanxia Wu + 1 more
Batch normalization (BN) is crucial for achieving state-of-the-art binary neural networks (BNNs). Unlike full-precision neural networks, BNNs restrict activations to discrete values ${-1,1}$, which requires a renewed understanding and research of the role and significance of the BN layers in BNNs. Many studies notice…
84relevance
07
PPubMed2 Nov 2023
Towards accelerating model parallelism in distributed deep learning systems Towards accelerating model parallelism in distributed deep learning systems
Hyeonseong Choi, Byung Hyun Lee, Se Young Chun, Jaehwan Lee + 1 more
'Elena Loli Piccolomini'] Modern deep neural networks cannot be often trained on a single GPU due to large model size and large data size. Model parallelism splits a model for multiple GPUs, but making it scalable and seamless is challenging due to different information sharing among GPUs with communication overhead.…
83relevance
08
PPubMed31 Aug 2018
Deep Supervised Learning Using Local Errors
Hesham Mostafa, Vishwajith Ramesh, Gert Cauwenberghs
Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from higher layers. Learning using delayed and non-local errors makes it hard to reconcile…
78relevance
09
PPubMed25 Dec 2020
Using Out-of-Batch Reference Populations to Improve Untargeted Metabolomics for Screening Inborn Errors of Metabolism
Michiel Bongaerts, Ramon Bonte, Serwet Demirdas, Edwin H. Jacobs + 7 more
'Esmee Oussoren' 'Ans T. van der Ploeg' 'Margreet A. E. M. Wagenmakers' 'Robert M. W. Hofstra' 'Henk J. Blom' 'Marcel J. T. Reinders' 'George J. G. Ruijter'] Untargeted metabolomics is an emerging technology in the laboratory diagnosis of inborn errors of metabolism (IEM). Analysis of a large number of reference…
77relevance
10
PPubMed3 Jan 2022
PresB-Net: parametric binarized neural network with learnable activations and shuffled grouped convolution
Jungwoo Shin, HyunJin Kim, Yilun Shang
In this study, we present a novel performance-enhancing binarized neural network model called PresB-Net: Parametric Binarized Neural Network. A binarized neural network (BNN) model can achieve fast output computation with low hardware costs by using binarized weights and features. However, performance degradation is…
76relevance
11
PPubMed29 Apr 2019
Bearing Fault Diagnosis Based on the Switchable Normalization SSGAN with 1-D Representation of Vibration Signals as Input
Dongdong Zhao, Feng Liu, He Meng
The bearing is a component of the support shaft that guides the rotational movement of the shaft, widely used in the mechanical industry and also called a mechanical joint. In bearing fault diagnosis, the accuracy much depends on the feature extraction, which always needs a lot of training samples and classification in…
74relevance
12
PPubMed28 Dec 2021
Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers †
Baihan Lin, Shu-Tao Xia, Bin Chen
Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the Minimum Description Length (MDL) principle. Treating the neural network…
73relevance

Results for batch normalization

Lightweight Convolutional Neural Network and Its Application in Rolling Bearing Fault Diagnosis under Variable Working Conditions

Revisiting Batch Normalization for Training Low-Latency Deep Spiking Neural Networks From Scratch

CytofIn enables integrated analysis of public mass cytometry datasets using generalized anchors

Instance Segmentation Based on Improved Self-Adaptive Normalization

Improving Network Training on Resource-Constrained Devices via Habituation Normalization †

Attention-Based Batch Normalization for Binary Neural Networks

Towards accelerating model parallelism in distributed deep learning systems Towards accelerating model parallelism in distributed deep learning systems

Deep Supervised Learning Using Local Errors

Using Out-of-Batch Reference Populations to Improve Untargeted Metabolomics for Screening Inborn Errors of Metabolism

PresB-Net: parametric binarized neural network with learnable activations and shuffled grouped convolution

Bearing Fault Diagnosis Based on the Switchable Normalization SSGAN with 1-D Representation of Vibration Signals as Input

Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers †

Lightweight Convolutional Neural Network and Its Application in Rolling Bearing Fault Diagnosis under Variable Working Conditions

Revisiting Batch Normalization for Training Low-Latency Deep Spiking Neural Networks From Scratch

CytofIn enables integrated analysis of public mass cytometry datasets using generalized anchors

Instance Segmentation Based on Improved Self-Adaptive Normalization

Improving Network Training on Resource-Constrained Devices via Habituation Normalization †

Attention-Based Batch Normalization for Binary Neural Networks

Towards accelerating model parallelism in distributed deep learning systems Towards accelerating model parallelism in distributed deep learning systems

Deep Supervised Learning Using Local Errors

Using Out-of-Batch Reference Populations to Improve Untargeted Metabolomics for Screening Inborn Errors of Metabolism

PresB-Net: parametric binarized neural network with learnable activations and shuffled grouped convolution

Bearing Fault Diagnosis Based on the Switchable Normalization SSGAN with 1-D Representation of Vibration Signals as Input

Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers †