Improve Python/NumPy code

[kir0ul]

At the moment, to convert the Cell data structure from Matlab, standard Python lists are used. Could be worth using Awkward Array to make computations faster and allow some broadcasting, see:

• https://awkward-array.org/
• https://github.com/jpivarski-talks/2020-02-27-irishep-poster/blob/master/pivarski-irishep-poster.pdf
• https://github.com/jpivarski-talks/2022-07-25-cssi-meeting-poster/blob/main/pivarski-awkward-cssi-poster.pdf

[kir0ul]

• [x] Maybe activity[j] and delta[j + 1] could be converted to a matrix to remove the need to check for the dimension of the array.

[kir0ul]

The code could be abstracted a bit more to higher level concepts, e.g., it could make sense to call higher level functions like a forward_pass(), backward_pass(), activation() (instead of copy/pasting several times the full length sigmoid function).

Could borrow some ideas from this reference code: https://github.com/mnielsen/neural-networks-and-deep-learning/blob/master/src/network.py, taken from Neural Networks and Deep Learning by Michael Nielsen