Author: LazyProgrammer
-
loc 358 - into two numpy arrays, the inputs X and the targets T. X should be an N x D array, where N is the number of samples, and D is the dimensionality
-
loc 359 - T should be an N x K array
-
loc 359 - The raw data will be in the form of an N x 1 array where the elements are values from 0..9. You will need to turn it into an indicator matrix of size N x K where the values are 0 or 1.
-
loc 366 - def softmax(a): expA = np.exp(A) return expA / expA.sum(axis=1, keepdims=True)