Auto-creation of Effective Neural Network Architecture by Evolutionary Algorithm and ResNet for Image Classification *

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.