问题描述
我无法使用前馈网络.它是具有单个神经元的单层...
这些方程式有什么不对吗?
输出=全部(输入x相应的重量)之和
错误=所需的输出-神经元输出
体重变化=>新权重=旧权重+学习速率*错误*该突触的输入
如果不是这样的话，当我每次都经过3种输入的两种模式时，您可能会看到问题所在:
数据重量输出|需求|错误新重量
--------------------------------------...
334.6 | 0.00125126 | 257.953 | 342.2 | 84.247 | 281.892
340.1 | 0.563585 |
340.7 | 0.193304 |
--------------------------------------...
340 | 281.892 | 293,693 .....使砝码变得多余并且程序错误
342 | 287.088 |快速击中#INF，因为它无法处理....
347 | 287.223 |
非常感谢！
I can''t get my feedforward net to work. it''s a single layer one with a single neuron...
are any of these equations wrong?
output = sum of all (inputs x corresponding weight)
error = desired output - neuron output
weight change => new weight = old weight + learningrate*error*input for that synapse
if not maybe you can see whats wrong when i go through two patterns of 3 inputs each time:
Data | Weight | Output | Desired | Error | New Weight
--------------------------------------…
334.6 | 0.00125126 | 257.953 | 342.2 | 84.247 | 281.892
340.1 | 0.563585 |
340.7 | 0.193304 |
--------------------------------------…
340 | 281.892 | 293,693 ..... making weights rediculous and the program error
342 | 287.088 | hitting #INF fast because it cant handle it....
347 | 287.223 |
Many thanks!
推荐答案
这篇关于如何计算前馈净重?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！