7月12号笔记------------BP神经网网络理论知识
1.
Python机器学习神经网络算法理论（BP）
https://www.k2zone.cn/?p=992
2.
机器学习——前馈神经网络
https://www.cnblogs.com/NeilZhang/p/9347233.html
3.
基于BP算法的前馈神经网络
http://www.elecfans.com/d/619349.html
4.
神经网络分类
https://blog.csdn.net/m0_37102093/article/details/78030711
5
深入理解BP神经网络
https://www.jianshu.com/p/6ab6f53874f7
6.
经典的全连接前馈神经网络与BP
https://mp.weixin.qq.com/s?src=11×tamp=1594517792&ver=2455&signature=2iqFvp7gZadr4PMyZ8UwI8PUyHx2RCQvyEli7otr9XLMy0H2DT*7BqDVATvDvoC0zCzxschcSg7289kxXBk5bNy9bJtFNSoEfaukFR*6suK3owqvJe9G26LY-lvsthDh&new=1
梯度下降（Gradient Descent）小结
https://www.cnblogs.com/pinard/p/5970503.html
手撕BP神经网络算法---------手把手教你机器学习（入门篇）
https://zhuanlan.zhihu.com/p/109822533
6.1
秒懂神经网络---震惊！！！神经网络原来可以这么简单！
https://www.cnblogs.com/Renyi-Fan/p/10971234.html#_label0_9
总结的超级全面（特别好） good
7. 总结的超级全面（特别好） good
如何自己从零实现一个神经网络?
https://www.zhihu.com/question/314879954
最后附上小哥的博客链接：
https://victorzhou.com/（用谷歌浏览器打开：里面的英文会自动翻译）
https://victorzhou.com/page/2/
import numpy as np
def sigmoid(x):
# Sigmoid activation function: f(x) = 1 / (1 + e^(-x))
return 1 / (1 + np.exp(-x))
def deriv_sigmoid(x):
# Derivative of sigmoid: f'(x) = f(x) * (1 - f(x))
fx = sigmoid(x)
return fx * (1 - fx)
def mse_loss(y_true, y_pred):
# y_true and y_pred are numpy arrays of the same length.
return ((y_true - y_pred) ** 2).mean()
class OurNeuralNetwork:
'''
A neural network with:
- 2 inputs
- a hidden layer with 2 neurons (h1, h2)
- an output layer with 1 neuron (o1)
*** DISCLAIMER ***:
The code below is intended to be simple and educational, NOT optimal.
Real neural net code looks nothing like this. DO NOT use this code.
Instead, read/run it to understand how this specific network works.
'''
def __init__(self):
# Weights
self.w1 = np.random.normal()
self.w2 = np.random.normal()
self.w3 = np.random.normal()
self.w4 = np.random.normal()
self.w5 = np.random.normal()
self.w6 = np.random.normal()
# Biases
self.b1 = np.random.normal()
self.b2 = np.random.normal()
self.b3 = np.random.normal()
def feedforward(self, x):
# x is a numpy array with 2 elements.
h1 = sigmoid(self.w1 * x[0] + self.w2 * x[1] + self.b1)
h2 = sigmoid(self.w3 * x[0] + self.w4 * x[1] + self.b2)
o1 = sigmoid(self.w5 * h1 + self.w6 * h2 + self.b3)
return o1
def train(self, data, all_y_trues):
'''
- data is a (n x 2) numpy array, n = # of samples in the dataset.
- all_y_trues is a numpy array with n elements.
Elements in all_y_trues correspond to those in data.
'''
learn_rate = 0.1
epochs = 1000 # number of times to loop through the entire dataset
for epoch in range(epochs):
for x, y_true in zip(data, all_y_trues):
# --- Do a feedforward (we'll need these values later)
sum_h1 = self.w1 * x[0] + self.w2 * x[1] + self.b1
h1 = sigmoid(sum_h1)
sum_h2 = self.w3 * x[0] + self.w4 * x[1] + self.b2
h2 = sigmoid(sum_h2)
sum_o1 = self.w5 * h1 + self.w6 * h2 + self.b3
o1 = sigmoid(sum_o1)
y_pred = o1
# --- Calculate partial derivatives.
# --- Naming: p_L_p_w1 stands for "partial L partial w1"
p_L_p_ypred = -2 * (y_true - y_pred)
# Neuron o1
p_ypred_p_w5 = h1 * deriv_sigmoid(sum_o1)
p_ypred_p_w6 = h2 * deriv_sigmoid(sum_o1)
p_ypred_p_b3 = deriv_sigmoid(sum_o1)
p_ypred_p_h1 = self.w5 * deriv_sigmoid(sum_o1)
p_ypred_p_h2 = self.w6 * deriv_sigmoid(sum_o1)
# Neuron h1
p_h1_p_w1 = x[0] * deriv_sigmoid(sum_h1)
p_h1_p_w2 = x[1] * deriv_sigmoid(sum_h1)
p_h1_p_b1 = deriv_sigmoid(sum_h1)
# Neuron h2
p_h2_p_w3 = x[0] * deriv_sigmoid(sum_h2)
p_h2_p_w4 = x[1] * deriv_sigmoid(sum_h2)
p_h2_p_b2 = deriv_sigmoid(sum_h2)
# --- Update weights and biases
# Neuron h1
self.w1 -= learn_rate * p_L_p_ypred * p_ypred_p_h1 * p_h1_p_w1
self.w2 -= learn_rate * p_L_p_ypred * p_ypred_p_h1 * p_h1_p_w2
self.b1 -= learn_rate * p_L_p_ypred * p_ypred_p_h1 * p_h1_p_b1
# Neuron h2
self.w3 -= learn_rate * p_L_p_ypred * p_ypred_p_h2 * p_h2_p_w3
self.w4 -= learn_rate * p_L_p_ypred * p_ypred_p_h2 * p_h2_p_w4
self.b2 -= learn_rate * p_L_p_ypred * p_ypred_p_h2 * p_h2_p_b2
# Neuron o1
self.w5 -= learn_rate * p_L_p_ypred * p_ypred_p_w5
self.w6 -= learn_rate * p_L_p_ypred * p_ypred_p_w6
self.b3 -= learn_rate * p_L_p_ypred * p_ypred_p_b3
# --- Calculate total loss at the end of each epoch
if epoch % 10 == 0:
y_preds = np.apply_along_axis(self.feedforward, 1, data)
loss = mse_loss(all_y_trues, y_preds)
print("Epoch %d loss: %.3f" % (epoch, loss))
# Define dataset
data = np.array([
[-2, -1], # Alice
[25, 6], # Bob
[17, 4], # Charlie
[-15, -6], # Diana
])
all_y_trues = np.array([
1, # Alice
0, # Bob
0, # Charlie
1, # Diana
])
# Train our neural network!
network = OurNeuralNetwork()
network.train(data, all_y_trues)
# Make some predictions
emily = np.array([-7, -3]) # 128 pounds, 63 inches
frank = np.array([20, 2]) # 155 pounds, 68 inches
print("Emily: %.3f" % network.feedforward(emily)) # 0.951 - F
print("Frank: %.3f" % network.feedforward(frank)) # 0.039 - M
8.
numpy全新文档
https://numpy.org/doc/stable/search.html?q=&check_keywords=yes&area=default
详细介绍
http://www.imooc.com/article/260174
医学图像分析最新综述：走向深度
http://www.dataguru.cn/article-14539-1.html
医学图像分析主要包含的模式识别任务是检测/定位、分割、配准、分类。常见的医学影像包括Brain、Breast、Eye、Chest、Abdomen等。
