# 手撕神经网络：从零开始实现一个简单的神经网络（python）

28 篇文章 12 订阅

## 手撕神经网络：从零开始实现一个简单的神经网络

### 2. 网络结构

z 1 = x W 1 + b 1 a 1 = tanh ⁡ ( z 1 ) = e z 1 − e − z 1 e z 1 + e − z 1 z 2 = a 1 W 2 + b 2 y ^ = a 2 = s o f t m a x ( z 2 ) \begin{aligned} z_1 & = xW_1 + b_1 \\ a_1 & = \tanh(z_1) = \frac{e^{z_1} - e^{-{z_1}}}{e^{z_1} + e^{-{z_1}}} \\ z_2 & = a_1W_2 + b_2 \\ \hat{y} & = a_2 = \mathrm{softmax}(z_2) \end{aligned}

l o s s = − ∑ k = 1 K y k l n y k ^ loss = - \sum_{k=1}^{K}y_k ln\hat{y_k}

δ 3 = ∂ L ∂ z 2 = y ^ − y δ 2 = ∂ L ∂ z 1 = ( 1 − tanh ⁡ 2 z 1 ) ∘ δ 3 W 2 T ∂ L ∂ W 2 = a 1 T δ 3 ∂ L ∂ b 2 = δ 3 ∂ L ∂ W 1 = x T δ 2 ∂ L ∂ b 1 = δ 2 \begin{aligned} & \delta_3 = \frac{\partial{L}}{\partial{z_2}} = \hat{y} - y \\ & \delta_2 = \frac{\partial{L}}{\partial{z_1}} = (1 - \tanh^2z_1) \circ \delta_3W_2^T \\ & \frac{\partial{L}}{\partial{W_2}} = a_1^T \delta_3 \\ & \frac{\partial{L}}{\partial{b_2}} = \delta_3\\ & \frac{\partial{L}}{\partial{W_1}} = x^T \delta_2\\ & \frac{\partial{L}}{\partial{b_1}} = \delta_2 \\ \end{aligned}

### 4. Code

ipython 代码如下。也可以直接参考 nn-from-scratch。虽然这只是一个简单的 nn 模型，但是也可以体会调参的乐趣了，比如设置小的学习率，或者给 SGD 加上 momentum，增加神经元的个数（nn_hdim），或者增加神经元的层数等都能减小 loss。

# Package imports
import matplotlib.pyplot as plt
import numpy as np
import sklearn
import sklearn.datasets
import sklearn.linear_model
import matplotlib

# Display plots inline and change default figure size
%matplotlib inline
matplotlib.rcParams['figure.figsize'] = (10.0, 8.0)

# Generate a dataset and plot it
np.random.seed(0)
# Generate 200 points
X, y = sklearn.datasets.make_moons(200, noise=0.20)
plt.scatter(X[:,0], X[:,1], s=40, c=y, cmap=plt.cm.Spectral)

num_examples = len(X) # training set size
nn_input_dim = 2 # input layer dimensionality
nn_output_dim = 2 # output layer dimensionality

# Gradient descent parameters (I picked these by hand)
epsilon = 0.01 # learning rate for gradient descent
reg_lambda = 0.01 # regularization strength

# Helper function to plot a decision boundary.
def plot_decision_boundary(pred_func):
# Set min and max values and give it some padding
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
h = 0.01
# Generate a grid of points with distance h between them
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
# Predict the function value for the whole gid
Z = pred_func(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
# Plot the contour and training examples
plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Spectral)

# Helper function to evaluate the total loss on the dataset
def calculate_loss(model):
W1, b1, W2, b2 = model['W1'], model['b1'], model['W2'], model['b2']
# Forward propagation to calculate our predictions
z1 = X.dot(W1) + b1
a1 = np.tanh(z1)
z2 = a1.dot(W2) + b2
exp_scores = np.exp(z2)
probs = exp_scores / np.sum(exp_scores, axis=1, keepdims=True)
# Calculating the loss
corect_logprobs = -np.log(probs[range(num_examples), y])
data_loss = np.sum(corect_logprobs)
# Add regulatization term to loss (optional)
data_loss += reg_lambda/2 * (np.sum(np.square(W1)) + np.sum(np.square(W2)))
return 1./num_examples * data_loss

# Helper function to predict an output (0 or 1)
def predict(model, x):
W1, b1, W2, b2 = model['W1'], model['b1'], model['W2'], model['b2']
# Forward propagation
z1 = x.dot(W1) + b1
a1 = np.tanh(z1)
z2 = a1.dot(W2) + b2
exp_scores = np.exp(z2)
probs = exp_scores / np.sum(exp_scores, axis=1, keepdims=True)
return np.argmax(probs, axis=1)

# This function learns parameters for the neural network and returns the model.
# - nn_hdim: Number of nodes in the hidden layer
# - num_passes: Number of passes through the training data for gradient descent
# - print_loss: If True, print the loss every 1000 iterations
def build_model(nn_hdim, num_passes=20000, print_loss=False):

# Initialize the parameters to random values. We need to learn these.
np.random.seed(0)
W1 = np.random.randn(nn_input_dim, nn_hdim) / np.sqrt(nn_input_dim)
b1 = np.zeros((1, nn_hdim))
W2 = np.random.randn(nn_hdim, nn_output_dim) / np.sqrt(nn_hdim)
b2 = np.zeros((1, nn_output_dim))

# This is what we return at the end
model = {}

# Gradient descent. For each batch...
for i in range(0, num_passes):

# Forward propagation
z1 = X.dot(W1) + b1
a1 = np.tanh(z1)
z2 = a1.dot(W2) + b2
exp_scores = np.exp(z2)
probs = exp_scores / np.sum(exp_scores, axis=1, keepdims=True)

# Backpropagation
delta3 = probs
delta3[range(num_examples), y] -= 1
dW2 = (a1.T).dot(delta3)
db2 = np.sum(delta3, axis=0, keepdims=True)
delta2 = delta3.dot(W2.T) * (1 - np.power(a1, 2))
dW1 = np.dot(X.T, delta2)
db1 = np.sum(delta2, axis=0)

# Add regularization terms (b1 and b2 don't have regularization terms)
dW2 += reg_lambda * W2
dW1 += reg_lambda * W1

# Gradient descent parameter update
W1 += -epsilon * dW1
b1 += -epsilon * db1
W2 += -epsilon * dW2
b2 += -epsilon * db2

# Assign new parameters to the model
model = { 'W1': W1, 'b1': b1, 'W2': W2, 'b2': b2}

# Optionally print the loss.
# This is expensive because it uses the whole dataset, so we don't want to do it too often.
if print_loss and i % 1000 == 0:
print("Loss after iteration %i: %f" %(i, calculate_loss(model)))

return model

# Build a model with a 3-dimensional hidden layer
model = build_model(3, print_loss=True)

# Plot the decision boundary
plot_decision_boundary(lambda x: predict(model, x))
plt.title("Decision Boundary for hidden layer size 3")



• 3
点赞
• 17
收藏
觉得还不错? 一键收藏
• 打赏
• 0
评论
03-19 2549
04-25 4300
01-05
02-16 220
12-28 2088
08-03 76
08-16 1370
02-09 105
06-12
08-03
08-24 306

### “相关推荐”对你有帮助么？

• 非常没帮助
• 没帮助
• 一般
• 有帮助
• 非常有帮助

kuweicai

¥1 ¥2 ¥4 ¥6 ¥10 ¥20

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。