-
摘要: 从二进前向网络的稳健要求出发,提出了稳健分类的概念,在此基础上给出了稳健分 类超平面的一般形式,从而如果二进前向网络的每一神经元都是稳健神经元,则网络的连接权 仅为-1,0或+1,每一神经元的阈值也只为二分之一的基阈值加上一处于有限区域上整数的 辅阈值,并且辅阈值为神经元各个输入对其的贡献之和.稳健二进前向网络的这些性质使得网 络不仅稳健能力强,而且易于做到隐节点数少、连接少、易于实现.
-
关键词:
- 分类/稳健分类 /
- 分类超平面/稳健分类超平面 /
- 神经元/稳健神经元 /
- 连接权 /
- 阈值和辅阈值
Abstract: From the requirement of robust classification capability of binary feedfor-ward neural networks (BNNs), the notion of robust classification is provided, and the general equation form of robust classification hyperplanes is presented. From this general equation, if a BNN is constructed by only robust neurons, each connection weight can take only -1, 0 or+1 and the threshold of each neuron in the net is a simple addition of base threshold of 1/2 and a complement shreshold ranged in a valid integer region. Also presented in this paper is that the threshold of each neuron is a summation of contributions from each input of this neuron. All of these characteristcs are of much importance in constructing a BNN with the greatest robustness, less number of hidden neurons and less number of connections in the net. It is also shown that the robust BNN particularly facilitates VLSI implementation.
计量
- 文章访问数: 2156
- HTML全文浏览量: 40
- PDF下载量: 902
- 被引次数: 0