A structure optimization framework for feed-forward neural networks using sparse representation

doi:10.1016/j.knosys.2016.06.026

Return

A structure optimization framework for feed-forward neural networks using sparse representation

2016-10-01

PRE

杨

杨杰 (Jie Yang)

Jun Ma *

DOI：10.1016/j.knosys.2016.06.026

Original

Original request for help

Save

Abstract

En 中文

Traditionally, optimizing the structure of a feed-forward neural-network is time-consuming and it needs to balance the trade-off between the network size and network performance. In this paper, a sparse representation based framework, termed SRS, is introduced to generate a small-sized network structure without compromising the network performance. Based on the forward selection strategy, the SRS framework selects significant elements (weights or hidden neurons) from the initial network that minimize the residual output error. The main advantage of the SRS framework is that it is able to optimize the network structure and training performance simultaneously. As a result, the training error is reduced while the number of selected elements increases. The efficiency and robustness of the SRS framework are evaluated based on several benchmark datasets. Experimental results indicate that the SRS framework performs favourably compared to alternative structure optimization algorithms. (C) 2016 Elsevier B.V. All rights reserved.

Keywords:

Neural networks

Structure optimization

Sparse representation

Network pruning

Network construction

Single measurement vector

Multiple measurement vector

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.