Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic-Reference-Cited by-同舟云学术

Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic

Published:2021-11 Issue: Volume:119 Page:108057
ISSN:0031-3203
Container-title:Pattern Recognition
language:en
Short-container-title:Pattern Recognition

Author:

Gowdra Nidhi^ORCID,Sinha Roopak,MacDonell Stephen^ORCID,Yan Wei Qi

Publisher

Elsevier BV

Subject

Artificial Intelligence,Computer Vision and Pattern Recognition,Signal Processing,Software

Reference38 articles.

1. Imagenet classification with deep convolutional neural networks;Krizhevsky,2012

2. Approximation by superpositions of a sigmoidal function;Cybenko;Mathematics of control, signals and systems,1989

3. Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping;Caruana,2001

4. A mathematical theory of deep convolutional neural networks for feature extraction;Wiatowski;IEEE Trans. Inf. Theory,2018

5. Understanding deep convolutional networks;Mallat;Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences,2016

Cited by 7 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Deep learning-based fatigue damage segmentation of wind turbine blades under complex dynamic thermal backgrounds;Structural Health Monitoring;2023-05-16

2. Representation and compression of Residual Neural Networks through a multilayer network based approach;Expert Systems with Applications;2023-04

3. Energy and Entropy based Intelligence Metric for Performance Estimation in DNNs;2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC);2023-02-20

4. An Abstraction Neural Network Generator for Efficient Formal Verification;Communications in Computer and Information Science;2023

5. Generative Adversarial Networks and Siamese Nets;Texts in Computer Science;2023