Closed selfint closed 3 years ago
How to: (roughly)
Inputs:
Output:
Calculation: errors * prev_activations.T
This yields an NxM matrix (Nx1 • 1xM = NxM)
works, but maybe there is a better way to use ndarray to perform the transposes (instead of using from_shape_vec)
from_shape_vec
How to: (roughly)
Inputs:
Output:
Calculation: errors * prev_activations.T
This yields an NxM matrix (Nx1 • 1xM = NxM)