神经网络(3)

# after the for clause, we have 'sigma_x(partial derivation of weight corresponding to cost function)' as well as
    # sigma_x(partial derivation of bias corresponding to cost function). it leaves us only to fill them up in the equations above, which
    # is done by the following
    self.weights = [w-(eta/len(mini_batch))*nw for w, nw in zip(self.weights, nabla_w)]
    self.biases = [b-(eta/len(mini_batch))*nb for b, nb in zip(self.biases, nabla_b)]

def SGD(self, training_data, epochs, mini_batch_size, eta,
        test_data=None):
    """Train the neural network using mini-batch stochastic
    gradient descent.  The "training_data" is a list of tuples
    "(x, y)" representing the training inputs and the desired
    outputs.  The other non-optional parameters are
    self-explanatory.  If "test_data" is provided then the
    network will be evaluated against the test data after each
    epoch, and partial progress printed out.  This is useful for
    tracking progress, but slows things down substantially.
    eta is the learning rate
    """