神经网络正弦逼近 [英] Neural network sine approximation

问题描述

花了几天的时间未能使用神经网络进行Q学习后，我决定回到基础知识，并进行简单的函数逼近，以查看一切是否正常工作，以及某些参数如何影响学习过程. 这是我想出的代码

After spending days failing to use neural network for Q learning, I decided to go back to the basics and do a simple function approximation to see if everything was working correctly and see how some parameters affected the learning process. Here is the code that I came up with

from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt
import random
import numpy
from sklearn.preprocessing import MinMaxScaler

regressor = Sequential()
regressor.add(Dense(units=20, activation='sigmoid', kernel_initializer='uniform', input_dim=1))
regressor.add(Dense(units=20, activation='sigmoid', kernel_initializer='uniform'))
regressor.add(Dense(units=20, activation='sigmoid', kernel_initializer='uniform'))
regressor.add(Dense(units=1))
regressor.compile(loss='mean_squared_error', optimizer='sgd')
#regressor = ExtraTreesRegressor()

N = 5000
X = numpy.empty((N,))
Y = numpy.empty((N,))

for i in range(N):
    X[i] = random.uniform(-10, 10)
X = numpy.sort(X).reshape(-1, 1)

for i in range(N):
    Y[i] = numpy.sin(X[i])
Y = Y.reshape(-1, 1)

X_scaler = MinMaxScaler()
Y_scaler = MinMaxScaler()
X = X_scaler.fit_transform(X)
Y = Y_scaler.fit_transform(Y)

regressor.fit(X, Y, epochs=2, verbose=1, batch_size=32)
#regressor.fit(X, Y.reshape(5000,))

x = numpy.mgrid[-10:10:100*1j]
x = x.reshape(-1, 1)
y = numpy.mgrid[-10:10:100*1j]
y = y.reshape(-1, 1)
x = X_scaler.fit_transform(x)

for i in range(len(x)):
    y[i] = regressor.predict(numpy.array([x[i]]))

plt.figure()
plt.plot(X_scaler.inverse_transform(x), Y_scaler.inverse_transform(y))
plt.plot(X_scaler.inverse_transform(X), Y_scaler.inverse_transform(Y))

问题是我所有的预测值都在0左右.如您所见，我使用了来自sklearn的ExtraTreesRegressor(带注释的行)来检查协议是否正确.那么我的神经网络怎么了?为什么它不起作用?

The problem is that all my predictions are around 0 in value. As you can see I used an ExtraTreesRegressor from sklearn (commented lines) to check that the protocol is actually correct. So what is wrong with my neural network ? Why is it not working ?

(我要解决的实际问题是使用神经网络计算山地车问题的Q函数.它与该函数逼近器有何不同?)

(The actual problem that I'm trying to solve is to compute the Q function for the mountain car problem using neural network. How is it different from this function approximator ?)

推荐答案

进行以下更改:

• 对relu
的激活
• 删除kernel_initializer(即保留默认 'glorot_uniform')
• 亚当优化器
• 100个纪元

• Activations to relu
• Remove kernel_initializer (i.e. leave the default 'glorot_uniform')
• Adam optimizer
• 100 epochs

即

regressor = Sequential()
regressor.add(Dense(units=20, activation='relu', input_dim=1)) 
regressor.add(Dense(units=20, activation='relu')) 
regressor.add(Dense(units=20, activation='relu')) 
regressor.add(Dense(units=1))
regressor.compile(loss='mean_squared_error', optimizer='adam')

regressor.fit(X, Y, epochs=100, verbose=1, batch_size=32)

，其余代码保持不变，结果如下:

and the rest of your code unchanged, here is the result:

修补匠，一次又一次...

Tinker, again and again...

这篇关于神经网络正弦逼近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！