Proceedings ArticleDOI
Auto-creation of Effective Neural Network Architecture by Evolutionary Algorithm and ResNet for Image Classification *
Zefeng Chen,Yuren Zhou,Zhengxin Huang +2 more
- pp 3895-3900
TLDR
Experimental results show that the network architecture created by the proposed algorithm can achieve higher classification accuracy than the reference network architectures and the ones evolved by other state-of-the-art evolutionary topology design methods, demonstrating the effectiveness of the proposed algorithms on automatically creating network architectures.Abstract:
In this paper, we propose a novel evolutionary algorithm for automatically creating neural network architectures. The proposed algorithm utilizes basic building blocks from existing advanced networks to initialize the population. During the evolutionary process, the algorithm generates new individuals (that is, new networks) which are constructed by making use of different blocks from different networks. Moreover, the encoding scheme, genetic operators and fitness function are well designed. As a result, the generated network architecture, which has a strong heterogeneous property, tends to integrate the merits of existing advanced networks. Experimental results show that the network architecture created by the proposed algorithm can achieve higher classification accuracy than the reference network architectures and the ones evolved by other state-of-the-art evolutionary topology design methods, demonstrating the effectiveness of the proposed algorithm on automatically creating network architectures.read more
Citations
More filters
Posted Content
A Survey on Evolutionary Neural Architecture Search
TL;DR: This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design.
Journal ArticleDOI
A Self-Adaptive Mutation Neural Architecture Search Algorithm Based on Blocks
TL;DR: In this article, a self-adaptive mutation neural architecture search algorithm based on ResNet blocks and DenseNet blocks is proposed, which makes the algorithm adaptively adjust the mutation strategies during the evolution process to achieve better exploration.
Journal ArticleDOI
A Survey on Evolutionary Neural Architecture Search
TL;DR: In this article , the authors reviewed over 200 papers of most recent Evolutionary Computation-based Neural Architecture Search (NAS) methods in light of the core components, to systematically discuss their design principles as well as justifications on the design.
Book ChapterDOI
Constrained evolutionary piecemeal training to design convolutional neural networks
Dolly Sapra,Andy D. Pimentel +1 more
TL;DR: It is demonstrated that network architecture and its coefficients can be learned together by unifying concepts of evolutionary search within a population based traditional training process.
Journal ArticleDOI
Lights and shadows in Evolutionary Deep Learning: Taxonomy, critical methodological analysis, cases of study, learned lessons, recommendations and challenges
Aritz D. Martinez,Javier Del Ser,Esther Villar-Rodriguez,Eneko Osaba,Javier Poyatos,Siham Tabik,Daniel Molina,Francisco Herrera +7 more
TL;DR: This work comprehensively review and critically examine contributions made so far based on three axes - optimization and taxonomy, critical analysis, and challenges - which outline a complete vision of a merger of two technologies drawing up an exciting future for this area of fusion research.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Posted Content
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: This work proposes a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit and derives a robust initialization method that particularly considers the rectifier nonlinearities.
Proceedings ArticleDOI
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: In this paper, a Parametric Rectified Linear Unit (PReLU) was proposed to improve model fitting with nearly zero extra computational cost and little overfitting risk, which achieved a 4.94% top-5 test error on ImageNet 2012 classification dataset.
Book ChapterDOI
Identity Mappings in Deep Residual Networks
TL;DR: In this paper, the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation.