Completely Automated CNN Architecture Design Based on Blocks

By Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen. 2020

301 citations recorded by the source corpus.

The performance of convolutional neural networks (CNNs) highly relies on their architectures. In order to design a CNN with promising performance, extensive expertise in both CNNs and the investigated problem domain is required, which is not necessarily available to every interested user. To address this problem, we propose to automatically evolve CNN architectures by using a genetic algorithm (GA) based on ResNet and DenseNet blocks. The proposed algorithm is completely automatic in designing CNN architectures. In particular, neither preprocessing before it starts nor postprocessing in terms of CNNs is needed. Furthermore, the proposed algorithm does not require users with domain knowledge on CNNs, the investigated problem, or even GAs. The proposed algorithm is evaluated on the CIFAR10 and CIFAR100 benchmark data sets against 18 state-of-the-art peer competitors. Experimental results show that the proposed algorithm outperforms the state-of-the-art CNNs hand-crafted and the CNNs designed by automatic peer competitors in terms of the classification performance and achieves a competitive classification accuracy against semiautomatic peer competitors. In addition, the proposed algorithm consumes much less computational resource than most peer competitors in finding the best CNN architectures.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

Citations in the corpus

• Surrogate-Assisted Evolutionary Deep Learning Using an End-to-End Random Forest-Based Performance Predictor (2020, methodology): “sentative EDL, which is mainly based on the reasons that: 1) it shows promising performance among existing EDLs [48] and 2) the source code of AE-CNN is available to the public.”
• A Survey on Evolutionary Neural Architecture Search (2020, methodology): “are randomly generated in the limited space, and it has been adopted by many methods, such as [9], [21], and [67].”