用正弦函数训练神经网络 [英] Train neural network with sine function

问题描述

我想用sine()函数训练一个神经网络.

I want to train a neural network with the sine() function.

当前，我使用此代码和(大脑 gem):

Currently I use this code and the (cerebrum gem):

require 'cerebrum'

input = Array.new
300.times do |i|
  inputH = Hash.new
  inputH[:input]=[i]
  sinus = Math::sin(i)
  inputH[:output] = [sinus]
  input.push(inputH)

end

network = Cerebrum.new

network.train(input, {
  error_threshold: 0.00005,
  iterations:      40000,
  log:             true,
  log_period:      1000,
  learning_rate:   0.3
})


res = Array.new
300.times do |i|
  result = network.run([i])
  res.push(result[0])
end

puts "#{res}"

但是它不起作用，如果我运行训练有素的网络，我会得到一些奇怪的输出值(而不是得到正弦曲线的一部分).

But it does not work, if I run the trained network I get some weird output values (instead of getting a part of the sine curve).

那么，我做错了什么?

So, what I am doing wrong?

推荐答案

Cerebrum是一种非常基本且缓慢的NN实现. Ruby中有更好的选择，例如ruby-fann gem.

Cerebrum is a very basic and slow NN implementation. There are better options in Ruby, such as ruby-fann gem.

您的问题很可能是网络过于简单.您尚未指定任何隐藏层-看起来代码为您的案例分配了一个默认的隐藏层，其中包含3个神经元.

Most likely your problem is the network is too simple. You have not specified any hidden layers - it looks like the code assigns a default hidden layer with 3 neurons in it for your case.

尝试类似的东西:

network = Cerebrum.new({
  learning_rate:  0.01,
  momentum:       0.9,
  hidden_layers:  [100]
})

并希望它永远需要训练，再加上效果还不是很好.

and expect it to take forever to train, plus still not be very good.

此外，您对300个输出的选择范围太广-对于网络而言，它看起来像是噪声，并且在点之间插值效果不好.神经网络无法以某种方式找出哦，那一定是正弦波"并与其匹配.相反，它在点之间进行插值-一次在多个维度上进行操作时，就会出现聪明点，也许是发现了手动检查无法轻易发现的结构.为了给它提供学习某些东西的合理机会，我建议您给它一些密集点，例如您当前使用sinus = Math::sin(i)的位置，而不是使用:

Also, your choice of 300 outputs is too broad - to the network it will look mostly like noise and it won't interpolate well between points. A neural network does not somehow figure out "oh, that must be a sine wave" and match to it. Instead it interpolates between the points - the clever bit happens when it does so in multiple dimensions at once, perhaps finding structure that you could not spot so easily with a manual inspection. To give it a reasonable chance of learning something, I suggest you give it much denser points e.g. where you currently have sinus = Math::sin(i) instead use:

sinus = Math::sin(i.to_f/10)

在正弦波中仍然有将近5次迭代.希望这足以证明网络可以学习任意功能.

That's still almost 5 iterations through the sine wave. Which should hopefully be enough to prove that the network can learn an arbitrary function.

这篇关于用正弦函数训练神经网络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IT屋！