Evolutionary Convolutional Neural Network Optimization with Cross-Tasks Transfer Strategy

Electronics

Tongfei Liu¹  Peng Li¹  Di Lu¹  Huabing Wang²  Zhao Wang² 

[1] Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education, Xidian University, No. 2 South TaiBai Road, Xi’an 710071, China;State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System (CEMEE), Luoyang 471003, China;

关键词: evolutionary algorithm;    convolutional neural network;    transfer learning;    image classification;   

DOI  :  10.3390/electronics10151857

来源: DOAJ

【 摘 要 】

Convolutional neural networks (CNNs) have shown great success in a variety of real-world applications and the outstanding performance of the state-of-the-art CNNs is primarily driven by the elaborate architecture. Evolutionary convolutional neural network (ECNN) is a promising approach to design the optimal CNN architecture automatically. Nevertheless, most of the existing ECNN methods only focus on improving the performance of the discovered CNN architectures without considering the relevance between different classification tasks. Transfer learning is a human-like learning approach and has been introduced to solve complex problems in the domain of evolutionary algorithms (EAs). In this paper, an effective ECNN optimization method with cross-tasks transfer strategy (CTS) is proposed to facilitate the evolution process. The proposed method is then evaluated on benchmark image classification datasets as a case study. The experimental results show that the proposed method can not only speed up the evolutionary process significantly but also achieve competitive classification accuracy. To be specific, our proposed method can reach the same accuracy at least 40 iterations early and an improvement of accuracy for 0.88% and 3.12% on MNIST-FASHION and CIFAR10 datasets compared with ECNN, respectively.

【 授权许可】

Unknown