Tools

Matrix inversion

sqrt_inverse_matrix_semi_positive(matrix[, ...])

Compute the square root of the inverse of a semi-positive definite matrix.

Helpers

compute_optimal_added_parameters(matrix_s, ...)	Compute the optimal added parameters for a given layer.
compute_output_shape_conv(input_shape, conv)	Compute the output shape of a convolutional layer
compute_mask_tensor_t(input_shape, conv)	Compute the tensor T For: - input tensor: B[-1] in (S[-1], H[-1]W[-1]) and (S[-1], H'[-1]W'[-1]) after the pooling - output tensor: B in (S, HW) - conv kernel tensor: W in (S, S[-1], Hd, Wd) T is the tensor in (HW, HdWd, H'[-1]W'[-1]) such that: B = W T B[-1]