RankOrderedAutoencoder.py 文件源码

def forward_prop(self):
        # backprop
        self.output_error = np.sum(self.errors * self.weights, axis=0).reshape(1, -1)
        self.output_error /= self.weights.shape[0]
        self.output_error *= self.derivative(self.output_raw, self.output_error)
        # clip gradient to not exceed zero
        self.output_error[self.output_raw > 0] = \
            np.maximum(-self.output_raw[self.output_raw > 0],self.output_error[self.output_raw > 0])
        self.output_error[self.output_raw < 0] = \
            np.minimum(-self.output_raw[self.output_raw < 0],self.output_error[self.output_raw < 0])