Physics and Python stuff. Most of the videos here are either adapted from class lectures or solving physics problems. I really like to use numerical calculations without all the fancy programming ...

I use Python 3 and Jupyter Notebooks to generate plots and equations with linear regression on Kaggle data. I checked the correlations and built a basic machine learning model with this dataset.

Logistic regression can in principle be modified to handle problems where the item to predict can take one of three or more values instead of just one of two possible values. The is sometimes called ...

Each weight cell is initialized to a random value between -0.01 and +0.01. The model bias is initialized to zero. An alternative design is to place the weights and bias into a Python class. The code ...