Title: A block-encoding method for evolving neural network architecture
Authors: Xiaohu Shi; Hongyan Guo; Chunguo Wu; Yanchun Liang; Zhiyong Chang
Addresses: Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun, 130012, China ' Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun, 130012, China ' Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun, 130012, China ' School of Computer Science, Zhuhai College of Science and Technology, Zhuhai, 519041, China ' Key Laboratory of Bionic Engineering of Ministry of Education, College of Biological and Agricultural Engineering, Jilin University, Changchun 130022, China
Abstract: The architecture and parameters of convolutional neural networks have an important impact on their performance. To overcome the difficulties of most existing neural architecture search (NAS) methods, including fixed network architecture and huge computing cost, this paper proposes a block-encoding based on neural architecture evolving method. A new block-encoding method is designed to divide the convolutional neural network architecture into blocks consisting of multiple functional layers. Efficient mutating operation is designed to speed up evolutionary search and expand the evolution space of network architecture. Finally, the optimal evolved network is converted into an all-convolutional neural network with fewer parameters and more concise architecture. The experiments on image datasets indicate that the proposed method can greatly reduce network parameters and searching time, achieve competitive classification accuracy and directly obtain the corresponding all-convolutional neural network architecture.
Keywords: evolving neural networks; network architecture; block-encoding; search space; all convolutional network.
DOI: 10.1504/IJBIC.2021.117436
International Journal of Bio-Inspired Computation, 2021 Vol.18 No.1, pp.27 - 37
Received: 16 Jan 2021
Accepted: 14 Mar 2021
Published online: 06 Sep 2021 *