My homework for CAS Advanced Machine Learning 2022/23 in Bern. Course M6 is about the mathematical foundations of Machine Learning. It was taught by Kinga. Task: develop your own neuronal network class.

All parts are numbered. The final Class can be found in the full_NN script. Apllications are all scripts entitled with the prefix application.

The solution is based on many tutorials, namely:

• www.towardsdatascience.com/building-a-deep-neural-network-from-scratch-using-numpy-4f28a1df157a
• www.heartbeat.comet.ml/building-a-neural-network-from-scratch-using-python-part-2-testing-the-network-c1f0c1c9cbb0
• www.towardsdatascience.com/lets-code-a-neural-network-in-plain-numpy-ae7e74410795
• www.geeksforgeeks.org/implementation-of-neural-network-from-scratch-using-numpy/
• www.nnfs.org

todo:

• something something optimizer adam

• regularization

• model object automation