Automatically Evolving CNN Architectures Based on Blocks
This addresses the need for accessible CNN design for users lacking expertise, though it is incremental as it builds on existing blocks and genetic algorithms.
The paper tackles the problem of designing high-performance CNN architectures without requiring expert knowledge by proposing a genetic algorithm that automatically evolves architectures using ResNet and DenseNet blocks. It outperforms 18 state-of-the-art competitors on CIFAR10 and CIFAR100 in classification accuracy and consumes less time.
The performance of Convolutional Neural Networks (CNNs) highly relies on their architectures. In order to design a CNN with promising performance, extended expertise in both CNNs and the investigated problem is required, which is not necessarily held by every user interested in CNNs or the problem domain. In this paper, we propose to automatically evolve CNN architectures by using a genetic algorithm based on ResNet blocks and DenseNet blocks. The proposed algorithm is \textbf{completely} automatic in designing CNN architectures, particularly, neither pre-processing before it starts nor post-processing on the designed CNN is needed. Furthermore, the proposed algorithm does not require users with domain knowledge on CNNs, the investigated problem or even genetic algorithms. The proposed algorithm is evaluated on CIFAR10 and CIFAR100 against 18 state-of-the-art peer competitors. Experimental results show that it outperforms state-of-the-art CNNs hand-crafted and CNNs designed by automatic peer competitors in terms of the classification accuracy, and achieves the competitive classification accuracy against semi-automatic peer competitors. In addition, the proposed algorithm consumes much less time than most peer competitors in finding the best CNN architectures.