神经网络输出分组0.5？
我尝试编写一个神经网络系统，但即使运行简单的 AND/OR/NOR 类型问题，输出似乎也集中在 0.5（对于 -1 的偏差）和 0.7（对于 1 的偏差）。 它看起来并不完全“错误”... AND 模式中的 1,1 看起来确实比其余的要高，而 OR 中的 0,0 看起来要低一些，但它们仍然全部分组，所以这是有争议的。
我想知道a）我是否犯了一些明显的错误，或者b）是否有任何调试神经网络的建议......因为你不能总是准确地追踪答案的来源......
谢谢！
麦克风
I tried to write a Neural Network system, but even running through simple AND/OR/NOR type problems, the outputs seem to group around 0.5 (for a bias of -1) and 0.7 (for a bias of 1).
It doesn't look exactly "wrong"... The 1,1 in the AND pattern does seem higher than the rest and the 0,0 in the OR looks lower, but they are still all grouped so it's debatable.
I was wondering a) if there's some obvious mistake I've made or b) if there's any advice for debugging Neural Nets... seeing as you can't always track back exactly where an answer came from...
Thanks!
Mike
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（2）
a) 如果没有更多信息就无法判断。
对于b）我发现的最好方法是为我的网络架构的小型测试版本提供一组预先计算的向量和权重，并使用一些调试代码将网络状态转储到csv文件中，以便我可以查看在 Excel 中。
对于单个模式和已知的网络初始状态，网络的前向（和后向）传递应该完全可以手动计算，因此最好有一个候选模式，或者如果您可以完全手动执行，则有几个候选模式是个好主意为您的测试枚举。实际上并不像听起来那么糟糕。
这样做还有一个额外的好处，它可以增强您对算法如何工作的理解，并使您从不同的角度再次检查您的实现。
祝你好运。
PS 无耻插件反向传播博客条目这里...
for a) it's impossible to tell without more information.
for b) the best way I have found is to have a pre-calculated set of vectors and weights for a small test version of my network architecture and to have some debug code that dumps the network state out to a csv file so I can look at it in Excel.
The forward (and backward) passes of your network should be completely calculable manually for a single pattern, and a known network initial state, so it's a good idea to have a candidate pattern, or a couple if you can bear doing it manually, fully enumerated for your tests. It's not actually as bad as it sounds.
Doing this has the added advantage that it reinforces your understanding of how the algorithm works and will cause you to check your implementation again from a different standpoint.
good luck.
P.S. shameless plug on backprop blog entry here...
我回答了类似的问题，并发布了一些您可以测试的值：
人工神经网络基准< /a>
使用这些值来测试您的神经网络。即使您使用不同的语言，您的输出也应该非常接近地匹配值......您应该能够毫无问题地匹配小数点后至少 6 位数字。
I answered a similar question and I posted some values you can test against:
Artificial neural networks benchmark
Use those values in order to test your neural network. Your outputs should match the values VERY closely, even if you're using different languages... you should be able match at least 6 digits after the decimal without a problem.