文章列表的Sigmoid函数由以下方程式定义： 对于x的导数可以自己表示。 Sigmoid函数的曲线如s曲线所示。 Sigmoid函数的次数用python打印Sigmoid函数曲线。 结果，如果希望Sigmoid函数计算numpy阵列，则可以用以下符号表示
Sigmoid函数由以下公式定义：
对于其x的导数可以自己表示：
一类s曲线的Sigmoid函数的图：
Sigmoid函数的级数表示：
Sigmoid的一般数值：
用python打印Sigmoid函数曲线： importnumpyasnpimportmatplotlib.pyplotaspltdefsigmoid (x ) :return1.0/) 1NP.exp ) sssp 0.1 ) sigmoid _ outputs=sigmoid (sigmoid _ inputs )打印(sigmoidfunctioninput :3360 { }.format ) sigmoid _ sid . format ) sigmoid_outputs ) PLT.plot ) sigmoid_inputs，sigmoid _ outputs (PLT.xlabel (sigmoid inputs ) ) PLT.plot 结果： sigmoidfunctioninput : [-1.000000000 e01-9.800000000 e00-9.70000000 e00-9.60000000 e00-9.50000000 0000000 e00-9.000000000 e00-8.80000000000 e00-8.7000000000 e000-8.60000000000 e00-8.300000000000 e00 00-7.900000000 e00-7.800000000 e00-7.700000000 e00-7.6000000。 00-7.40000000 e00-7.300000000 e00-7.20000000000 e00-7.0000000000 e00-6.9000000000 e00-6.700000000 40000000 e00-6.300000000 e00-6.200000000 e00-6.100000000 e00-5.8000000000 e00-5.500000000 200000000 e00-5.10000000000 e00-5.000000000000 e00-4.800000000000 e00-5.00000000000.6000000000 . 200000000 e00-4.100000000 e00-4.0000000000 e00-3.60000000000 e00-3.50000000000 e00-3.4000000000 - 3.0000000 e00-2.900000000 e00-2.6000000000 e00-2.50000000000 e00-2.3000000000000 e0000000000 0000000000000000 000 e00-1.700000000 e00-1.6000000000 e00-1.50000000000 e00-1.30000000000 e00 7.00000000 e-01-6.0000000000 e-01-5.000000000 e-01-4.0000000000 e-01-3.000000000
-01 -1.00000000e-01 -3.55271368e-14 1.00000000e-01 2.00000000e-01 3.00000000e-01 4.00000000e-01 5.00000000e-01 6.00000000e-01 7.00000000e-01 8.00000000e-01 9.00000000e-01 1.00000000e+00 1.10000000e+00 1.20000000e+00 1.30000000e+00 1.40000000e+00 1.50000000e+00 1.60000000e+00 1.70000000e+00 1.80000000e+00 1.90000000e+00 2.00000000e+00 2.10000000e+00 2.20000000e+00 2.30000000e+00 2.40000000e+00 2.50000000e+00 2.60000000e+00 2.70000000e+00 2.80000000e+00 2.90000000e+00 3.00000000e+00 3.10000000e+00 3.20000000e+00 3.30000000e+00 3.40000000e+00 3.50000000e+00 3.60000000e+00 3.70000000e+00 3.80000000e+00 3.90000000e+00 4.00000000e+00 4.10000000e+00 4.20000000e+00 4.30000000e+00 4.40000000e+00 4.50000000e+00 4.60000000e+00 4.70000000e+00 4.80000000e+00 4.90000000e+00 5.00000000e+00 5.10000000e+00 5.20000000e+00 5.30000000e+00 5.40000000e+00 5.50000000e+00 5.60000000e+00 5.70000000e+00 5.80000000e+00 5.90000000e+00 6.00000000e+00 6.10000000e+00 6.20000000e+00 6.30000000e+00 6.40000000e+00 6.50000000e+00 6.60000000e+00 6.70000000e+00 6.80000000e+00 6.90000000e+00 7.00000000e+00 7.10000000e+00 7.20000000e+00 7.30000000e+00 7.40000000e+00 7.50000000e+00 7.60000000e+00 7.70000000e+00 7.80000000e+00 7.90000000e+00 8.00000000e+00 8.10000000e+00 8.20000000e+00 8.30000000e+00 8.40000000e+00 8.50000000e+00 8.60000000e+00 8.70000000e+00 8.80000000e+00 8.90000000e+00 9.00000000e+00 9.10000000e+00 9.20000000e+00 9.30000000e+00 9.40000000e+00 9.50000000e+00 9.60000000e+00 9.70000000e+00 9.80000000e+00 9.90000000e+00]Sigmoid Function Output :: [4.53978687e-05 5.01721647e-05 5.54485247e-05 6.12797396e-05 6.77241496e-05 7.48462275e-05 8.27172229e-05 9.14158739e-05 1.01029194e-04 1.11653341e-04 1.23394576e-04 1.36370327e-04 1.50710358e-04 1.66558065e-04 1.84071905e-04 2.03426978e-04 2.24816770e-04 2.48455082e-04 2.74578156e-04 3.03447030e-04 3.35350130e-04 3.70606141e-04 4.09567165e-04 4.52622223e-04 5.00201107e-04 5.52778637e-04 6.10879359e-04 6.75082731e-04 7.46028834e-04 8.24424686e-04 9.11051194e-04 1.00677082e-03 1.11253603e-03 1.22939862e-03 1.35851995e-03 1.50118226e-03 1.65880108e-03 1.83293894e-03 2.02532039e-03 2.23784852e-03 2.47262316e-03 2.73196076e-03 3.01841632e-03 3.33480731e-03 3.68423990e-03 4.07013772e-03 4.49627316e-03 4.96680165e-03 5.48629890e-03 6.05980149e-03 6.69285092e-03 7.39154134e-03 8.16257115e-03 9.01329865e-03 9.95180187e-03 1.09869426e-02 1.21284350e-02 1.33869178e-02 1.47740317e-02 1.63024994e-02 1.79862100e-02 1.98403057e-02 2.18812709e-02 2.41270214e-02 2.65969936e-02 2.93122308e-02 3.22954647e-02 3.55711893e-02 3.91657228e-02 4.31072549e-02 4.74258732e-02 5.21535631e-02 5.73241759e-02 6.29733561e-02 6.91384203e-02 7.58581800e-02 8.31726965e-02 9.11229610e-02 9.97504891e-02 1.09096821e-01 1.19202922e-01 1.30108474e-01 1.41851065e-01 1.54465265e-01 1.67981615e-01 1.82425524e-01 1.97816111e-01 2.14165017e-01 2.31475217e-01 2.49739894e-01 2.68941421e-01 2.89050497e-01 3.10025519e-01 3.31812228e-01 3.54343694e-01 3.77540669e-01 4.01312340e-01 4.25557483e-01 4.50166003e-01 4.75020813e-01 5.00000000e-01 5.24979187e-01 5.49833997e-01 5.74442517e-01 5.98687660e-01 6.22459331e-01 6.45656306e-01 6.68187772e-01 6.89974481e-01 7.10949503e-01 7.31058579e-01 7.50260106e-01 7.68524783e-01 7.85834983e-01 8.02183889e-01 8.17574476e-01 8.32018385e-01 8.45534735e-01 8.58148935e-01 8.69891526e-01 8.80797078e-01 8.90903179e-01 9.00249511e-01 9.08877039e-01 9.16827304e-01 9.24141820e-01 9.30861580e-01 9.37026644e-01 9.42675824e-01 9.47846437e-01 9.52574127e-01 9.56892745e-01 9.60834277e-01 9.64428811e-01 9.67704535e-01 9.70687769e-01 9.73403006e-01 9.75872979e-01 9.78118729e-01 9.80159694e-01 9.82013790e-01 9.83697501e-01 9.85225968e-01 9.86613082e-01 9.87871565e-01 9.89013057e-01 9.90048198e-01 9.90986701e-01 9.91837429e-01 9.92608459e-01 9.93307149e-01 9.93940199e-01 9.94513701e-01 9.95033198e-01 9.95503727e-01 9.95929862e-01 想人陪的向日葵] 若想让sigmoid函数计算numpy数组，可用以下编码方式表示 def sigmoid(x): x_ravel = x.ravel() # 将numpy数组展平 length = len(x_ravel) y = [] for index in range(length): if x_ravel[index] >= 0: y.append(1.0 / (1 + np.exp(-x_ravel[index]))) else: y.append(np.exp(x_ravel[index]) / (np.exp(x_ravel[index]) + 1)) return np.array(y).reshape(x.shape)参考文章1：Sigmoid函数
参考文章2：python计算警告：overflow encountered in exp（指数函数溢出）（sigmoid函数的numpy数组计算方式）