Evolving Deep Convolutional Neural Networks for Image Classification

Evolutionary paradigms have been successfully applied to neural network designs for two decades. Unfortunately, these methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights. In this paper, we propose a new method using genetic algorithms for evolving the architectures and connection weight initialization values of a deep convolutional neural network to address image classification problems. In the proposed algorithm, an efficient variable-length gene encoding strategy is designed to represent the different building blocks and the potentially optimal depth in convolutional neural networks. In addition, a new representation…

• VU
  Victoria University of Wellington

  Awards: 209862/3580, 213150/3662
• NN
  National Natural Science Foundation of China

  Awards: 61803277, 61625204
• MF
  Marsden Fund

  Awards: VUW1209, VUW1615, VUW1509