scholarly journals Energy-Efficient Gabor Kernels in Neural Networks with Genetic Algorithm Training Method

Electronics ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 105 ◽  
Author(s):  
Fanjie Meng ◽  
Xinqing Wang ◽  
Faming Shao ◽  
Dong Wang ◽  
Xia Hua
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Neural Networks ◽  
Energy Efficient ◽  
Experimental Result ◽  
Training Method ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Deep Model

Deep-learning convolutional neural networks (CNNs) have proven to be successful in various cognitive applications with a multilayer structure. The high computational energy and time requirements hinder the practical application of CNNs; hence, the realization of a highly energy-efficient and fast-learning neural network has aroused interest. In this work, we address the computing-resource-saving problem by developing a deep model, termed the Gabor convolutional neural network (Gabor CNN), which incorporates highly expression-efficient Gabor kernels into CNNs. In order to effectively imitate the structural characteristics of traditional weight kernels, we improve upon the traditional Gabor filters, having stronger frequency and orientation representations. In addition, we propose a procedure to train Gabor CNNs, termed the fast training method (FTM). In FTM, we design a new training method based on the multipopulation genetic algorithm (MPGA) and evaluation structure to optimize improved Gabor kernels, but train the rest of the Gabor CNN parameters with back-propagation. The training of improved Gabor kernels with MPGA is much more energy-efficient with less samples and iterations. Simple tasks, like character recognition on the Mixed National Institute of Standards and Technology database (MNIST), traffic sign recognition on the German Traffic Sign Recognition Benchmark (GTSRB), and face detection on the Olivetti Research Laboratory database (ORL), are implemented using LeNet architecture. The experimental result of the Gabor CNN and MPGA training method shows a 17–19% reduction in computational energy and time and an 18–21% reduction in storage requirements with a less than 1% accuracy decrease. We eliminated a significant fraction of the computation-hungry components in the training process by incorporating highly expression-efficient Gabor kernels into CNNs.

Sign in / Sign up

Export Citation Format

Share Document