Neural Networks and Deep Learning week3 Planar data classification with a hidden layer

该实验作业的主要目的

1. 实现一个二元分类（多元分类就是分为目标类和非目标类两类）
2. 使用非线性激活函数（希望你还记得为什么，在哪里使用什么函数的原因）
3. 实现前向传播和后向传播

你可能对以下文献感兴趣

• http://scs.ryerson.ca/~aharley/neural-networks/  打不开了？？？
• http://cs231n.github.io/neural-networks-case-study/  多元分类（3元）

总体进程

载入文件

显示数据集

2 获取数据集信息

线性回归显示，发现效果不好，于是我们决定使用神经网络

总述一下我们神经网络的过程

4.1获取神经网络的一些信息（超参量）

4.2 初始化参数

4.3前向传播

4.3代价函数

4.3后向传播

4.3更新参数

4.4将模块化整合

4.5预测

由于我们已经模块化了神经网络，现在我们可以快速的对网络进行修改，比如修改隐藏层的大小

我们也可以用这个网络去测试其他集

在需要写代码的前面我将提示任务目标

Updates to Assignment

If you were working on the older version:

• Please click on the "Coursera" icon in the top right to open up the folder directory.
• Navigate to the folder: Week 3/ Planar data classification with one hidden layer. You can see your prior work in version 6b: "Planar data classification with one hidden layer v6b.ipynb"

List of bug fixes and enhancements

• Clarifies that the classifier will learn to classify regions as either red or blue.
• compute_cost function fixes np.squeeze by casting it as a float.
• compute_cost instructions clarify the purpose of np.squeeze.
• compute_cost clarifies that "parameters" parameter is not needed, but is kept in the function definition until the auto-grader is also updated.
• nn_model removes extraction of parameter values, as the entire parameter dictionary is passed to the invoked functions.

 

Planar data classification with one hidden layer

Welcome to your week 3 programming assignment. It's time to build your first neural network, which will have a hidden layer. You will see a big difference between this model and the one you implemented using logistic regression.

You will learn how to:

• Implement a 2-class classification neural network with a single hidden layer
• Use units with a non-linear activation function, such as tanh
• Compute the cross entropy loss
• Implement forward and backward propagation

 

1 - Packages

Let's first import all the packages that you will need during this assignment.

• numpy is the fundamental package for scientific computing with Python.
• sklearn provides simple and efficient tools for data mining and data analysis.
• matplotlib is a library for plotting graphs in Python.
• testCases provides some test examples to assess the correctness of your functions
• planar_utils provide various useful functions used in this assignment

# Package imports
import numpy as np
import matplotlib.pyplot as plt
from testCases_v2 import *
import sklearn
import sklearn.datasets
import sklearn.linear_model
from planar_utils import plot_decision_boundary, sigmoid, load_planar_dataset, load_extra_datasets

%matplotlib inline

np.random.seed(1) # set a seed so that the results are consistent

2 - Dataset

First, let's get the dataset you will work on. The following code will load a "flower" 2-class dataset into variables X and Y.

X, Y = load_planar_dataset()

Visualize the dataset using matplotlib. The data looks like a "flower" with some red (label y=0) and some blue (y=1) points. Your goal is to build a model to fit this data. In other words, we want the classifier to define regions as either red or blue.

# Visualize the data:
plt.scatter(X[0, :], X[1, :], c=Y, s=40, cmap=plt.cm.Spectral);

You have:

- a numpy-array (matrix) X that contains your features (x1, x2)
- a numpy-array (vector) Y that contains your labels (red:0, blue:1).

Lets first get a better sense of what our data is like.

Exercise: How many training examples do you have? In addition, what is the shape of the variables X and Y?

Hint: How do you get the shape of a numpy array? (help)

获取向量XY的大小信息

一般情况下，Y应为一个列向量(m,1) m行为示例的个数，1是因为我们结果只能输出一个，无法输出多个，X为(m,nx) m个实例，每一个实例中有nx的特征值

### START CODE HERE ### (≈ 3 lines of code)
shape_X = X.shape
shape_Y = Y.shape
m = X.shape[1]  # training set size
### END CODE HERE ###

print ('The shape of X is: ' + str(shape_X))
print ('The shape of Y is: ' + str(shape_Y))
print ('I have m = %d training examples!' % (m))

Expected Output:

shape of X	(2, 400)
shape of Y	(1, 400)
m	400

3 - Simple Logistic Regression

Before building a full neural network, lets first see how logistic regression performs on this problem. You can use sklearn's built-in functions to do that. Run the code below to train a logistic regression classifier on the dataset.

# Train the logistic regression classifier
clf = sklearn.linear_model.LogisticRegressionCV();
clf.fit(X.T, Y.T);

You can now plot the decision boundary of these models. Run the code below.

# Plot the decision boundary