感知器的动态稀疏化学习
Dynamic Dilution for Perceptron Training
-
摘要: 本文提出了一种感知器的动态稀疏化(dynamic dilution)概念,同时估计权值和减少神 经元间的连接权个数.动态稀疏化有效地克服了传统的静态稀疏化(先确定权值,然后减少连 接权个数)的缺陷.计算机实验结果说明了算法的优越性.Abstract: In this paper, a dynamic dilution concept for perceptrons is proposed, which estimates the weights and reduces the number of connections at the same time. The dynamic dilution overcomes the weakness of the static dilution. Computer simulations are conducted to show its advantages.
-
Key words:
- Perceptron /
- learning algorithm /
- dynamic dilution /
- static dilution
-
计量
- 文章访问数: 2845
- HTML全文浏览量: 194
- PDF下载量: 968
- 被引次数: 0
下载:
