GP-CNAS: Convolutional Neural Network Architecture Search with Genetic Programming

by   Yiheng Zhu, et al.

Convolutional neural networks (CNNs) are effective at solving difficult problems like visual recognition, speech recognition and natural language processing. However, performance gain comes at the cost of laborious trial-and-error in designing deeper CNN architectures. In this paper, a genetic programming (GP) framework for convolutional neural network architecture search, abbreviated as GP-CNAS, is proposed to automatically search for optimal CNN architectures. GP-CNAS encodes CNNs as trees where leaf nodes (GP terminals) are selected residual blocks and non-leaf nodes (GP functions) specify the block assembling procedure. Our tree-based representation enables easy design and flexible implementation of genetic operators. Specifically, we design a dynamic crossover operator that strikes a balance between exploration and exploitation, which emphasizes CNN complexity at early stage and CNN diversity at later stage. Therefore, the desired CNN architecture with balanced depth and width can be found within limited trials. Moreover, our GP-CNAS framework is highly compatible with other manually-designed and NAS-generated block types as well. Experimental results on the CIFAR-10 dataset show that GP-CNAS is competitive among the state-of-the-art automatic and semi-automatic NAS algorithms.



There are no comments yet.



Evolutionary NAS with Gene Expression Programming of Cellular Encoding

The renaissance of neural architecture search (NAS) has seen classical m...

Enhanced Gradient for Differentiable Architecture Search

In recent years, neural architecture search (NAS) methods have been prop...

Optimizing Convolutional Neural Network Architecture via Information Field

CNN architecture design has attracted tremendous attention of improving ...

A Novel Sleep Stage Classification Using CNN Generated by an Efficient Neural Architecture Search with a New Data Processing Trick

With the development of automatic sleep stage classification (ASSC) tech...

Evolutionary Neural Architecture Search Supporting Approximate Multipliers

There is a growing interest in automated neural architecture search (NAS...

An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints

Recently, there emerged revived interests of designing automatic program...

Soft Genetic Programming Binary Classifiers

The study of the classifier's design and it's usage is one of the most i...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.