Place the data into shared variables. This allows Theano to copy the data to the GPU, if one is available.

The sigmoid function.

The sigmoid function.

Return the number of inputs in ``data`` for which the neural network outputs the correct result. The neural network's output is assu

Return the output of the network if ``a`` is input.

Return the size of the dataset `data`.

Return the accuracy for the mini-batch.

Derivative of the sigmoid function.

Derivative of the sigmoid function.

Return the total cost for the data set ``data``. The flag ``convert`` should be set to False if the data set is the training data (

Train the neural network using mini-batch stochastic gradient descent. The ``training_data`` is a list of tuples ``(x, y)`` represent

Return a defaultdict whose keys are the digits 0 through 9. For each digit we compute a value which is the average darkness of training ima

Return a tuple ``(nabla_b, nabla_w)`` representing the gradient for the cost function C_x. ``nabla_b`` and ``nabla_w`` are layer-by-l

Return a tuple ``(nabla_b, nabla_w)`` representing the gradient for the cost function C_x. ``nabla_b`` and ``nabla_w`` are layer-by

Return the log-likelihood cost.

Return the vector of partial derivatives \partial C_x / \partial a for the output activations.

Initialize each weight using a Gaussian distribution with mean 0 and standard deviation 1 over the square root of the number of weig

Return the error delta from the output layer.

Return the number of test inputs for which the neural network outputs the correct result. Note that the neural network's output is ass

Return the output of the network if ``a`` is input.

Return the cost associated with an output ``a`` and desired output ``y``.

Return the digit whose average darkness in the training data is closest to the darkness of ``image``. Note that ``avgs`` is assumed to be a

Return the MNIST data as a tuple containing the training data, the validation data, and the test data. The ``training_data`` is returned as a

Update the network's weights and biases by applying gradient descent using backpropagation to a single mini batch. The ``mini_batch``

Update the network's weights and biases by applying gradient descent using backpropagation to a single mini batch. The ``mini_batch

Return a 10-dimensional unit vector with a 1.0 in the jth position and zeroes elsewhere. This is used to convert a digit (0...9) into a corre

Return a 10-dimensional unit vector with a 1.0 in the j'th position and zeroes elsewhere. This is used to convert a digit (0...9) into a co

Train the network using mini-batch stochastic gradient descent.

Train the neural network using mini-batch stochastic gradient descent. The ``training_data`` is a list of tuples ``(x, y)`` represe

The list ``sizes`` contains the number of neurons in the respective layers of the network. For example, if the list was [2, 3, 1] the

Takes a list of `layers`, describing the network architecture, and a value for the `mini_batch_size` to be used during training by sto

`filter_shape` is a tuple of length 4, whose entries are the number of filters, the number of input feature maps, the filter height, and the

The list ``sizes`` contains the number of neurons in the respective layers of the network. For example, if the list was [2, 3, 1] t

Return the accuracy for the mini-batch.

Return the error delta from the output layer. Note that the parameter ``z`` is not used by the method. It is included in the metho

Return the cost associated with an output ``a`` and desired output ``y``. Note that np.nan_to_num is used to ensure numerical stabi

Initialize the weights using a Gaussian distribution with mean 0 and standard deviation 1. Initialize the biases using a Gaussian d

Load a neural network from the file ``filename``. Returns an instance of Network.

Return a tuple containing ``(training_data, validation_data, test_data)``. Based on ``load_data``, but the format is more convenient for use i

Save the neural network to the file ``filename``.