EvoDCNN: An evolutionary deep convolutional neural network for image classification

Developing Deep Convolutional Neural Networks (DCNNs) for image classification is a complicated task that needs considerable effort and knowledge. By employing an evolutionary computation approach, one can automatically generate the network models. However, the Neuroevolution is computationally expen-sive, and in some cases it needs hundreds of GPU days for training. Therefore, there is a need to find opti-mum Neuroevolutionary models with minimum computation to deal with this problem. In this paper, by utilising a Genetic Algorithm (GA), we introduce EvoDCNN, as a block-based evolutionary model for developing an evolutionary deep convolutional network for image classification. Such that by using the proposed fixed-length encoding model, we can generate variable-length networks with high accuracy while using less computation. The proposed model by utilising a straightforward evolutionary framework is able to establish small networks with high classification accuracy. Eight datasets: CIFAR10, MNIST, and six versions of EMNIST, that include balanced and unbalanced datasets, are used for evaluation of the pro-posed model. We did a comprehensive evaluation where we compared the results with many previous works, and outperformed the previous state-of-the-art accuracy for classification of five of the datasets.(c) 2022 Published by Elsevier B.V.

Automated summary

This paper introduces EvoDCNN, a block-based evolutionary model for developing deep convolutional networks for image classification, using a genetic algorithm. By utilizing a fixed-length encoding model, variable-length networks can be generated with high accuracy and less computation. Comprehensive evaluations on multiple datasets show that the proposed model outperforms previous state-of-the-art accuracy for classification.