建站
咨詢
售后
建站咨詢
新聞中心
這里有您想知道的互聯(lián)網(wǎng)營銷解決方案
Python使用numpy實(shí)現(xiàn)BP神經(jīng)網(wǎng)絡(luò)-創(chuàng)新互聯(lián)
本文完全利用numpy實(shí)現(xiàn)一個(gè)簡單的BP神經(jīng)網(wǎng)絡(luò)，由于是做regression而不是classification，因此在這里輸出層選取的激勵(lì)函數(shù)就是f(x)=x。BP神經(jīng)網(wǎng)絡(luò)的具體原理此處不再介紹。
import numpy as np
class NeuralNetwork(object):
def __init__(self, input_nodes, hidden_nodes, output_nodes, learning_rate):
# Set number of nodes in input, hidden and output layers.設(shè)定輸入層、隱藏層和輸出層的node數(shù)目
self.input_nodes = input_nodes
self.hidden_nodes = hidden_nodes
self.output_nodes = output_nodes
# Initialize weights，初始化權(quán)重和學(xué)習(xí)速率
self.weights_input_to_hidden = np.random.normal(0.0, self.hidden_nodes**-0.5,
( self.hidden_nodes, self.input_nodes))
self.weights_hidden_to_output = np.random.normal(0.0, self.output_nodes**-0.5,
(self.output_nodes, self.hidden_nodes))
self.lr = learning_rate
# 隱藏層的激勵(lì)函數(shù)為sigmoid函數(shù)，Activation function is the sigmoid function
self.activation_function = (lambda x: 1/(1 + np.exp(-x)))
def train(self, inputs_list, targets_list):
# Convert inputs list to 2d array
inputs = np.array(inputs_list, ndmin=2).T # 輸入向量的shape為 [feature_diemension, 1]
targets = np.array(targets_list, ndmin=2).T
# 向前傳播，F(xiàn)orward pass
# TODO: Hidden layer
hidden_inputs = np.dot(self.weights_input_to_hidden, inputs) # signals into hidden layer
hidden_outputs = self.activation_function(hidden_inputs) # signals from hidden layer
# 輸出層，輸出層的激勵(lì)函數(shù)就是 y = x
final_inputs = np.dot(self.weights_hidden_to_output, hidden_outputs) # signals into final output layer
final_outputs = final_inputs # signals from final output layer
### 反向傳播 Backward pass，使用梯度下降對(duì)權(quán)重進(jìn)行更新 ###
# 輸出誤差
# Output layer error is the difference between desired target and actual output.
output_errors = (targets_list-final_outputs)
# 反向傳播誤差 Backpropagated error
# errors propagated to the hidden layer
hidden_errors = np.dot(output_errors, self.weights_hidden_to_output)*(hidden_outputs*(1-hidden_outputs)).T
# 更新權(quán)重 Update the weights
# 更新隱藏層與輸出層之間的權(quán)重 update hidden-to-output weights with gradient descent step
self.weights_hidden_to_output += output_errors * hidden_outputs.T * self.lr
# 更新輸入層與隱藏層之間的權(quán)重 update input-to-hidden weights with gradient descent step
self.weights_input_to_hidden += (inputs * hidden_errors * self.lr).T
# 進(jìn)行預(yù)測
def run(self, inputs_list):
# Run a forward pass through the network
inputs = np.array(inputs_list, ndmin=2).T
#### 實(shí)現(xiàn)向前傳播 Implement the forward pass here ####
# 隱藏層 Hidden layer
hidden_inputs = np.dot(self.weights_input_to_hidden, inputs) # signals into hidden layer
hidden_outputs = self.activation_function(hidden_inputs) # signals from hidden layer
# 輸出層 Output layer
final_inputs = np.dot(self.weights_hidden_to_output, hidden_outputs) # signals into final output layer
final_outputs = final_inputs # signals from final output layer
return final_outputs 另外有需要云服務(wù)器可以了解下創(chuàng)新互聯(lián)scvps.cn，海內(nèi)外云服務(wù)器15元起步，三天無理由+7*72小時(shí)售后在線，公司持有idc許可證，提供“云服務(wù)器、裸金屬服務(wù)器、高防服務(wù)器、香港服務(wù)器、美國服務(wù)器、虛擬主機(jī)、免備案服務(wù)器”等云主機(jī)租用服務(wù)以及企業(yè)上云的綜合解決方案，具有“安全穩(wěn)定、簡單易用、服務(wù)可用性高、性價(jià)比高”等特點(diǎn)與優(yōu)勢，專為企業(yè)上云打造定制，能夠滿足用戶豐富、多元化的應(yīng)用場景需求。
文章名稱：Python使用numpy實(shí)現(xiàn)BP神經(jīng)網(wǎng)絡(luò)-創(chuàng)新互聯(lián)
文章分享：http://fisionsoft.com.cn/article/eijoo.html
