Multi-Valued Neuron with Sigmoid Activation Function for Pattern Classification

• 作者: Shen-Fu Wu Shie-Jue Lee Yu-Shu Chiou
• 来源期刊: 电脑和通信(英文)
• 学科: 数学
• 关键词: PATTERN Classification MULTI-VALUED NEURON (MVN) DIFFERENTIABLE ACTIVATION Function Backpropagation
• 年，卷（期）: dnhtxyw_2014,（4）
• 页码范围: 172-181
• 页数: 10页
• 分类号: O1

摘要

Multi-Valued Neuron (MVN) was proposed for pattern classification. It operates with complex-valued inputs, outputs, and weights, and its learning algorithm is based on error-correcting rule. The activation function of MVN is not differentiable. Therefore, we can not apply backpropagation when constructing multilayer structures. In this paper, we propose a new neuron model, MVN-sig, to simulate the mechanism of MVN with differentiable activation function. We expect MVN-sig to achieve higher performance than MVN. We run several classification benchmark datasets to compare the performance of MVN-sig with that of MVN. The experimental results show a good potential to develop a multilayer networks based on MVN-sig.