def Dtanh(y): return 1-y*y def linear(x): return x def Dlinear(y): return 1 nn = NeuralNetwork(1, 1) nn.add(5, [tanh, Dtanh]) nn.add(5, [tanh, Dtanh]) nn.init([linear, Dlinear]) n = 25000 cost = [] for i in range(n): index = np.random.randint(0, N) x = data[index][0] y = data[index][1] c = nn.cost(x, y) cost.append(c) nn.train(x, y) if i % 100 == 0:
from nn import NeuralNetwork import numpy as np # lst = ['a', 'b', 'c'] # pool = cycle(lst) # for item in pool: # print(item) X = np.array([[0, 81, 75, 0]]) y = np.array([[1]]) nn = NeuralNetwork(X,y) nn.add(7) nn.fit(12,100,0.5,0.001)