最近學習了浙江大學的機器學習課程，又學習了一些內容，用python實現了bp神經網路
**如下：
#定義sigmoid和它的導數
import numpy as np
import random,math
defmake_matrix
(m,n)
:return np.random.random(size=
(m,n)
)def
sigmoid
(x):
return
1.0/
(1.0
+np.exp(
-x))
defsimgmoid_derivate
(x):
return x*(1
-x)#定義類
class
bpneuralnetwork
:def
__init__
(self)
:#輸入層
self.input_n =
0 self.hidden_n =
0 self.output_n =
0 self.input_cells =
self.hidden_cells =
self.output_cells =
self.input_weights =
self.output_weights =
self.input_correction =
self.output_correction =
defset_up
(self,ni,nh,no)
: self.input_n= ni
self.hidden_n = nh
self.output_n = no
#初始化cell
self.input_cells =
[1.0
]* self.input_n
self.hidden_cells =
[1.0
]* self.hidden_n
self.output_cells =
[1.0
]* self.output_n
# 初始化權重
self.input_weights = make_matrix(self.input_n,self.hidden_n)
self.output_weights = make_matrix(self.hidden_n,self.output_n)
#啟用#矯正矩陣
self.input_correction = make_matrix(self.input_n,self.hidden_n)
self.output_correction = make_matrix(self.hidden_n,self.output_n)
#第一次前饋
defpredict
(self,inputs)
:for i in
range
(self.input_n)
: self.input_cells[i]
= inputs[i]
for j in
range
(self.hidden_n)
: total =
0.0for i in
range
(self.input_n)
: total+=self.input_cells[i]
* self.input_weights[i]
[j]#若是連續的值需要修改啟用函式
self.hidden_cells[j]
= sigmoid(total)
#輸出層計算
for k in
range
(self.output_n)
: total =
0.0for j in
range
(self.output_n)
: total += self.hidden_cells[k]
*self.output_weights[k]
[j] self.output_cells[k]
= sigmoid(total)
return self.output_cells[:]
#反向傳播 學習率λ， 矯正率μ
defupdate
(self,x,y,learn,correct)
: self.predict(x)
#計算誤差
output_deltas =
[0.0
]*self.output_n
for o in
range
(self.output_n)
: error = y[0]
-self.output_cells[0]
#如果是連續值則無需計算
output_deltas[o]
= simgmoid_derivate(self.output_cells[o]
)* error
#計算隱藏層的誤差
hidden_deltas =
[0.0
]* self.hidden_n
for h in
range
(self.hidden_n)
:for o in
range
(self.output_n)
: change = output_deltas[o]
* self.hidden_cells[h]
#更新權重
self.output_weights[h]
[o]+= learn * change + correct * self.output_correction[h]
[o] self.output_correction[h]
[o]= change
#更新權重
for i in
range
(self.input_n)
:for h in
range
(self.hidden_n)
: change=hidden_deltas[h]
* self.input_cells[i]
self.input_weights[i]
[h]+= learn * change + correct * self.input_correction[i]
[h] self.input_correction[i]
[h]= change
#獲得全域性的誤差
error =
0.0for o in
range
(len
(y))
: error +=
0.5*
(y[o]
- self.output_cells[o])**
2return error
#開始訓練設定迭代次數 學習率和矯正率
deftrain
(self,x,y,limit=
1000000
,learn =
0.05
,correct =
0.1)
:for m in
range
(limit)
: error =
0.0for i in
range
(len
(x))
:#每次計算乙個
x_item =x[i]
y_item = y[i]
error+= self.update(x_item,y_item,learn,correct)
cases =[[
1,1]
,[2,
2],[
2,4]
,[1,
2],]
labels =[[
0],[
0],[
1],[
1]]t= bpneuralnetwork(
)t.set_up(2,
5,1)
t.train(cases,labels,
10000
,0.05
,0.1
)for case in cases:
print
(t.predict(case)
)
[0.5343332825010273]
[0.5379687945071842]
[0.5336526221969785]
效果並不是很好，可能**需要完善。
bp神經網路python實現
h1 np.maximum 0,np.dot x,w1 b1 計算第乙個隱層的啟用資料 nxh scores np.dot h1,w2 b2 神經元輸出 nxc scores scores np.reshape np.max scores,axis 1 n,1 nxc scores中的每個元素減去這...
C 實現神經BP神經網路
bp.h pragma once include include include include include using std vector using std exp using std cout using std endl class bp bp.cpp include bp.h bp ...
C 實現神經BP神經網路
bp.h pragma once include include include include include using std vector using std exp using std cout using std endl class bp bp.cpp include bp.h bp ...