def forward(network, x): W1, W2, W3 = network['W1'], network['W2'], network['W3'] b1, b2, b3 = network['b1'], network['b2'], network['b3'] a1 = c.np.dot(x, W1) + b1 z1 = sig.sigmoid(a1) a2 = c.np.dot(z1, W2) + b2 z2 = sig.sigmoid(a2) a3 = c.np.dot(z2, W3) + b3 Y = identity_function(a3) return Y
def predict(network, x): W1, W2, W3 = network['W1'], network['W2'], network['W3'] b1, b2, b3 = network['b1'], network['b2'], network['b3'] a1 = c.np.dot(x, W1) + b1 z1 = sig.sigmoid(a1) a2 = c.np.dot(z1, W2) + b2 z2 = sig.sigmoid(a2) a3 = c.np.dot(z2, W3) + b3 y = soft.softmax(a3) return y
def predict(self, x): W1, W2 = self.params['W1'], self.params['W2'] b1, b2 = self.params['b1'], self.params['b2'] a1 = c.np.dot(x, W1) + b1 z1 = sig.sigmoid(a1) a2 = c.np.dot(z1, W2) + b2 y = softmax(a2) return y
from lib import common as c from lib import sigmoid as sig X = c.np.array([1.0, 0.5]) W1 = c.np.array([[0.1, 0.3, 0.5], [0.2, 0.4, 0.6]]) B1 = c.np.array([0.1, 0.2, 0.3]) print(X.shape) print(W1.shape) print(B1.shape) A1 = c.np.dot(X, W1) + B1 print(A1) Z1 = sig.sigmoid(A1) W2 = c.np.array([[0.1, 0.4], [0.2, 0.5], [0.3, 0.6]]) B2 = c.np.array([0.1, 0.2]) print(Z1.shape) print(W2.shape) print(B2.shape) A2 = c.np.dot(Z1, W2) + B2 print(A2) Z2 = sig.sigmoid(A2) print(Z2) def identity_function(x): return x