Evolutionary NAS with Gene Expression Programming of Cellular Encoding

Abstract

The renaissance of neural architecture search (NAS) has seen classical methods such as genetic algorithms (GA) and genetic programming (GP) being exploited for convolutional neural network (CNN) architectures. While recent work have achieved promising performance on visual perception tasks, the direct encoding scheme of both GA and GP has functional complexity deficiency and does not scale well on large architectures like CNN. To address this, we present a new generative encoding scheme -- $symboliclineargenerativeencoding$ (SLGE) -- simple, yet powerful scheme which embeds local graph transformations in chromosomes of linear fixed-length string to develop CNN architectures of variant shapes and sizes via evolutionary process of gene expression programming. In experiments, the effectiveness of SLGE is shown in discovering architectures that improve the performance of the state-of-the-art handcrafted CNN architectures on CIFAR-10 and CIFAR-100 image classification tasks; and achieves a competitive classification error rate with the existing NAS methods using less GPU resources.

Accepted at IEEE SSCI 2020 (7 pages, 3 figures)

References in corpus (6)

• Neural Architecture Search with Reinforcement Learning
• Neural Architecture Search: A Survey
• DARTS: Differentiable Architecture Search
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
• Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing