Evolving Deep Convolutional Neural Networks by Variable-Length Particle Swarm Optimization for Image Classification

Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design. This paper focuses on utilising Particle Swarm Optimisation (PSO) to automatically search for the optimal architecture of CNNs without any manual work involved. In order to achieve the goal, three improvements are made based on traditional PSO. First, a novel encoding strategy inspired by computer networks which empowers particle vectors to easily encode CNN layers is proposed; Second, in order to allow the proposed method to learn variable-length CNN architectures, a Disabled layer is designed to hide some dimensions of the particle vector to achieve variable-length particles; Third, since the learning process on large data is slow, partial datasets are randomly picked for the evaluation to dramatically speed it up. The proposed algorithm is examined and compared with 12 existing algorithms including the state-of-art methods on three widely used image classification benchmark datasets. The experimental results show that the proposed algorithm is a strong competitor to the state-of-art algorithms in terms of classification error. This is the first work using PSO for automatically evolving the architectures of CNNs.

I. Introduction

Convolutional neural networks (CNNs) have demonstrated exceptional superiority in numerous machine learning tasks, such as speech recognition [1], sentence classification [2] and image classification [3]. However, designing the architectures of CNNs for specific tasks can be extremely complex, which can be seen from some existing efforts done by researchers, such as LeNet [4] [5], AlexNet [3], VGGNet [6] and GoogLeNet [7]. In addition, one cannot expect to get the optimal performance by applying the same architecture on various tasks, and the CNN architecture needs to be adjusted for each specific task, which will bring tremendous work as there are a large number of types of machine learning tasks in industry.