| 摘要: |
| 分类问题在前向神经网络研究中占有重要位置.本文利用几何方法给出一个二进制神经网络K（≥2）分类问题的新学习算法.算法通过训练点的几何位置与类别分析，建立一个四层前向神经网络，实现网络输入向量分类.本文算法的优点在于:保证学习收敛且收敛速度快于BP算法及已有的其他一些前向网络学习算法;算法可以确定神经网络的结构且能实现精确的向量分类.另外，算法所建神经网络由线性阀值单元组成，神经元突触权值和阀值均为整数，特别适合于集成电路实现. |
| 关键词: 神经网络 算法 收敛 训练 几何 |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国家自然科学基金、国家863高科技项目基金和山东省自然科学基金资助. |
|
| A GEOMETRICAL LEARNING ALGORITHM OF BINARY NEURAL NETWORKS FOR CLASSIFICATION |
|
ZHU Daming,MA Shaohan
|
| Abstract: |
| Binary to binary mapping for classification plays an important role in the researches on feed-forward-neural-network learning．In this paper，the geometrical method is employed to work out a new algorithm to train binary neural networks for classification．By analysis of every training vertex's geometrical location，the algorithm alwavs produces a neural network of four layers for a certain classification problem．The advantages of this algorithm are：it runs with guaranteed convergence and goes to converge much more quickly than BP and some other algorithms；it can determine the structure of the neural networks by learning SO that a precise classification is carried out．In addition，every neuron generated by the algorithm employs a hard-limit activation func-tion with integer synaptic weights，which makes the actual implementation by VLSI tech-nology more facilitated． |
| Key words: Neural networks algorithm convergence training geometry |
