Mathematical Methods of AI
A grab-bag of mathematically grounded AI work: explainable AI, recommender systems, Kalman filters and LDA topic modeling, with a focus on interpretability.

Several small projects on the mathematical side of AI: model-agnostic explainability methods, a Kalman filter I implemented, LDA topic discovery on a text corpus, and a recommender experiment. In each one I cared more about being able to explain the model than about raw accuracy.
Figures




Get in touch
Have a research idea, a role, or a question about one of these projects?
- Email mawangot2000@gmail.com The best way to reach me.
- LinkedIn tatenda-mawango For work and roles.(opens in a new tab)
- GitHub tatendamawango The code behind these projects.(opens in a new tab)
There's also a contact form.