Great pair of articles. Read both thoroughly and tried replicating your teachings to another problem.
There seems to be an issue with the matrices and I would like to know the fix. When adding layers, I want to have a 32 neurons with 94936 inputs (meaning the dataset has 30 rows and a couple more columns but I have splitted the set).
Lets say this the input matrix and output, respectively: Train Inputs Matrix(94936, 30); Train Outputs Matrix (94935, 30)
When running the sigmoid functions, Python outputs:
`ValueError: shapes (94936,30) and (94936,30) not aligned: 30 (dim 1) != 94936 (dim 0)`
All dimensions make sense so I am completely lost to find out what I am doing wrong when splitting the datasets.
Thanks in advance!