A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification

By Yanan Sun, Bing Xue, Mengjie Zhang. 2018

63 citations recorded by the source corpus.

© Springer Nature Switzerland AG 2018. Convolutional Neural Networks (CNNs) have demonstrated their superiority in image classification, and evolutionary computation (EC) methods have recently been surging to automatically design the architectures of CNNs to save the tedious work of manually designing CNNs. In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN. There are three new ideas in the proposed DECNN method. Firstly, an existing effective encoding scheme is refined to cater for variable-length CNN architectures; Secondly, the new mutation and crossover operators are developed for variable-length DE to optimise the hyperparameters of CNNs; Finally, the new second crossover is introduced to evolve the depth of the CNN architectures. The proposed algorithm is tested on six widely-used benchmark datasets and the results are compared to 12 state-of-the-art methods, which shows the proposed method is vigorously competitive to the state-of-the-art algorithms. Furthermore, the proposed method is also compared with a method using particle swarm optimisation with a similar encoding strategy named IPPSO, and the proposed DECNN outperforms IPPSO in terms of the accuracy.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures, Evolutionary Computation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bing Xue
2. Mengjie Zhang
3. Yanan Sun
4. Gary G. Yen
5. Yuqiao Liu
6. Yaochu Jin
7. Handing Wang
8. Ran Cheng

In Computer Vision and Pattern Recognition

1. Bing Xue
2. Mengjie Zhang
3. Yanan Sun
4. Gary G. Yen
5. Yuqiao Liu
6. Kate Saenko
7. Gabriella Csurka
8. Luc Van Gool

In Model Architectures

1. Bing Xue
2. Mengjie Zhang
3. Gary G. Yen
4. Yanan Sun

In Evolutionary Computation

1. Bing Xue
2. Mengjie Zhang
3. Gary G. Yen
4. Yuqiao Liu
5. Yanan Sun

Citations in the corpus

• A Survey on Evolutionary Neural Architecture Search (2020, methodology): “[75] tried to break the limit of maximum length using a Gaussian distribution initialization mechanism.”