def bpNet(dataSet, classLabels):
SampIn = mat(dataSet).T
expected = mat(classLabels)
m, n = shape(dataSet)
eb = 0.01
eta = 0.05
mc = 0.3
maxiter = 2000
errlist = []
nSampleNum = m
nSampleDim = n - 1
nHidden = 4
nOut = 1
hi_w = 2.0 * (random.rand(nHidden, nSampleDim) - 0.5)
hi_b = 2.0 * (random.rand(nHidden, 1) - 0.5)
hi_wb = mat(Untils.mergMatrix(mat(hi_w), mat(hi_b)))
out_w = 2.0 * (random.rand(nOut, nHidden) - 0.5)
out_b = 2.0 * (random.rand(nOut, 1) - 0.5)
out_wb = mat(Untils.mergMatrix(mat(out_w), mat(out_b)))
dout_wbOld = 0.0
dhi_wbOld = 0.0
for i in xrange(maxiter):
hi_input = hi_wb * SampIn
hi_output = logistic(hi_input)
hi2out = Untils.mergeMatrix(hi_output.T, ones((nSampleNum, 1))).T
out_input = out_wb * hi2out
out_output = logistic(out_input)
err = expected - out_output
sse = errorfunc(err)
errlist.append(sse)
if sse <= eb:
print "iteration:", i + 1
break
DELTA = multiply(err, dlogit(out_input, out_output))
wDelta = out_wb[:, :-1].T * DELTA
delta = multiply(wDelta, dlogit(hi_input, hi_output))
dout_wb = DELTA * hi2out.T
dhi_wb = delta * SampIn.T
if i == 0:
out_wb = out_wb + eta * dout_wb
hi_wb = hi_wb + eta * dhi_wb
else:
out_wb = out_wb + (1.0 - mc) * eta * dout_wb + mc * dout_wbOld
hi_wb = hi_wb + (1.0 - mc) * eta * dhi_wb + mc * dhi_wbOld
dout_wbOld = dout_wb
dhi_wbOld = dhi_wb
return errlist, out_wb, hi_wb
def bpNet(dataSet, classLabels):
# 数据集矩阵化
SampIn = mat(dataSet).T
expected = mat(classLabels)
m, n = shape(dataSet)
# 网络参数
eb = 0.01 # 误差容限
eta = 0.05 # 学习率
mc = 0.3 # 动量因子
maxiter = 2000 # 最大迭代次数
errlist = [] # 误差列表
# 构造网络
# 初始化网络
nSampNum = m
# 样本数量
nSampDim = n - 1
# 样本维度
nHidden = 4
# 隐含层神经元
nOut = 1
# 输出层
# 隐含层参数
hi_w = 2.0 * (random.rand(nHidden, nSampDim) - 0.5)
hi_b = 2.0 * (random.rand(nHidden, 1) - 0.5)
hi_wb = mat(Untils.mergMatrix(mat(hi_w), mat(hi_b)))
# 输出层参数
out_w = 2.0 * (random.rand(nOut, nHidden) - 0.5)
out_b = 2.0 * (random.rand(nOut, 1) - 0.5)
out_wb = mat(Untils.mergMatrix(mat(out_w), mat(out_b)))
# 默认旧权值
dout_wbOld = 0.0
dhi_wbOld = 0.0
for i in xrange(maxiter):
#1. 工作信号正向传播
#1.1 输入层到隐含层
hi_input = hi_wb * SampIn # hi_wb 4,n SampIn n,m
hi_output = logistic(hi_input)
print "hi_output.T.shape", hi_output.T.shape
hi2out = Untils.mergMatrix(hi_output.T, ones((nSampNum, 1))).T
#1.2 隐含层到输出层
out_input = out_wb * hi2out
out_output = logistic(out_input)
#2. 误差计算
err = expected - out_output
sse = errorfunc(err)
errlist.append(sse)
#2.1 判断是否收敛
if sse <= eb:
print "iteration:", i + 1
break
#3.误差信号反向传播
#3.1 DELTA为输出层到隐含层梯度
DELTA = multiply(err, dlogit(out_input, out_output))
wDelta = out_wb[:, :-1].T * DELTA
print "%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%"
print "err.shape", err.shape
print "dlogit(out_input,out_output).shape", dlogit(
out_input, out_output).shape
print "out_wb[:,:-1].T.shape", out_wb[:, :-1].T.shape
#3.2 delta为隐含层到输入层梯度
delta = multiply(wDelta, dlogit(hi_input, hi_output))
dout_wb = DELTA * hi2out.T
print "DELTA.shape", DELTA.shape
print "hi2out.T.shape", hi2out.T.shape
#3.3 输入层的权值更新
dhi_wb = delta * SampIn.T
#3.4 更新输出层和隐含层权值
if i == 0:
out_wb = out_wb + eta * dout_wb
hi_wb = hi_wb + eta * dhi_wb
else:
out_wb = out_wb + (1.0 - mc) * eta * dout_wb + mc * dout_wbOld
hi_wb = hi_wb + (1.0 - mc) * eta * dhi_wb + mc * dhi_wbOld
dout_wbOld = dout_wb
dhi_wbOld = dhi_wb
return errlist, out_wb, hi_wb
mc = 0.8 # 动量因子
maxiter = 1000 # 最大迭代次数
# 构造网络
# 初始化网络
nSampNum = m; # 样本数量
nSampDim = 2; # 样本维度
nHidden = 3; # 隐含层神经元
nOut = 1; # 输出层
# 隐含层参数
# net_Hidden * 3 一行代表一个隐含层节点
w = 2*(random.rand(nHidden,nSampDim)-1/2)
b = 2*(random.rand(nHidden,1)-1/2)
wex = mat(Untils.mergMatrix(mat(w),mat(b)))
# 输出层参数
W = 2*(random.rand(nOut,nHidden)-1/2)
B = 2*(random.rand(nOut,1)-1/2)
WEX = mat(Untils.mergMatrix(mat(W),mat(B)))
dWEXOld = [] ; dwexOld = [] # 初始化权值中间变量
# 训练
iteration = 0;
# 初始化误差变量
errRec = [];
for i in range(maxiter):
# 工作信号正向传播
hp = wex*SampIn
def bpNet(dataSet,classLabels):
# 数据集矩阵化
SampIn = mat(dataSet).T
expected = mat(classLabels)
[m,n] = shape(dataSet)
# 网络参数
eb = 0.01 # 误差容限
eta = 0.05 # 学习率
mc = 0.2 # 动量因子
maxiter = 2000 # 最大迭代次数
errRec = [] # 误差
# 构造网络
# 初始化网络
nSampNum = m; # 样本数量
nSampDim = n-1; # 样本维度
nHidden = 4; # 隐含层神经元
nOut = 1; # 输出层
# 输入层参数
# 隐含层参数
# net_Hidden * 3 一行代表一个隐含层节点
w = 2.0*(random.rand(nHidden,nSampDim)-1.0/2.0)
b = 2.0*(random.rand(nHidden,1)-1.0/2.0)
wex = mat(Untils.mergMatrix(mat(w),mat(b)))
# 输出层参数
W = 2.0*(random.rand(nOut,nHidden)-1.0/2.0)
B = 2.0*(random.rand(nOut,1)-1.0/2.0)
WEX = mat(Untils.mergMatrix(mat(W),mat(B)))
dWEXOld = 0.0 ; dwexOld = 0.0
# 训练
iteration = 0.0;
for i in range(maxiter):
# 1. 工作信号正向传播
hp = wex*SampIn
tau = logistic(hp)
tauex = Untils.mergMatrix(tau.T, ones((nSampNum,1))).T
HM = WEX*tauex
out = logistic(HM)
err = expected - out
sse = sumsqr(err)
errRec.append(sse);
# 判断是否收敛
iteration = iteration + 1
if sse <= eb:
print "iteration:",i
break;
# 2.误差信号反向传播
# DELTA和delta为局部梯度
DELTA = multiply(err,dlogit(HM,out))
wDelta = W.T*DELTA
delta = multiply(wDelta,dlogit(hp,tau))
dWEX = DELTA*tauex.T
dwex = delta*SampIn.T
# 3.更新权值
if i == 0:
WEX = WEX + eta * dWEX
wex = wex + eta * dwex
else :
WEX = WEX + (1.0 - mc)*eta*dWEX + mc * dWEXOld
wex = wex + (1.0 - mc)*eta*dwex + mc * dwexOld
dWEXOld = dWEX
dwexOld = dwex
W = WEX[:,0:nHidden]
return errRec,WEX,wex
mc = 0.8 # 动量因子
maxiter = 1000 # 最大迭代次数
# 构造网络
# 初始化网络
nSampNum = m; # 样本数量
nSampDim = 2; # 样本维度
nHidden = 3; # 隐含层神经元
nOut = 1; # 输出层
# 隐含层参数
# net_Hidden * 3 一行代表一个隐含层节点
w = 2*(random.rand(nHidden,nSampDim)-1/2)
b = 2*(random.rand(nHidden,1)-1/2)
wex = mat(Untils.mergMatrix(mat(w),mat(b)))
# 输出层参数
W = 2*(random.rand(nOut,nHidden)-1/2)
B = 2*(random.rand(nOut,1)-1/2)
WEX = mat(Untils.mergMatrix(mat(W),mat(B)))
dWEXOld = [] ; dwexOld = [] # 初始化权值中间变量
# 训练
iteration = 0;
# 初始化误差变量
errRec = [];
for i in range(maxiter):
# 工作信号正向传播
hp = wex*SampIn