AI 351: A Mathematical Approach to Machine Learning

Most machine learning workflows involve working with data, creating models, using hyperparameters to optimize model, saving and inferencing the trained models. This class introduces you to mathematical foundations of machine learning and a complete machine learning (ML) workflow implemented in PyTorch, a popular ML framework for Python.

Resources

Projects

1. Linear Regression

2. KMeans

3. Implementing a Neural Network in Numpy

4. Implementing a Neural Network in Pytorch

5. A DenseNet example through Pytorch

Literature

• Understanding Deep Learning, Simon J. D. Prince

• Artificial Intelligence: A modern approach (4th edition)
  Author's website:  https://aima.cs.berkeley.edu/

• The mathematics of deep learning, https://arxiv.org/abs/2105.04026

• Machine Learning book , S. Raschka, et al. 

• Bishop, Christopher. Neural Networks for Pattern Recognition. New York, NY: Oxford University Press, 1995. ISBN: 9780198538646.

• Duda, Richard, Peter Hart, and David Stork. Pattern Classification. 2nd ed. New York, NY: Wiley-Interscience, 2000. ISBN: 9780471056690.

• Hastie, T., R. Tibshirani, and J. H. Friedman. The Elements of Statistical Learning: Data Mining, Inference and Prediction. New York, NY: Springer, 2001. ISBN: 9780387952840.

  • • The Elements of Statistical Learning   (author's website)

• Probabilistic Machine Learning, Kevin Murphy

• MacKay, David. Information Theory, Inference, and Learning Algorithms. Cambridge, UK: Cambridge University Press, 2003. ISBN: 9780521642989. Available on-line here.

• Mitchell, Tom. Machine Learning. New York, NY: McGraw-Hill, 1997. ISBN: 9780070428072.

Links of interests

• Mathematics in Machine Learning, AMS Special session, April 19-21, 2024

• Oxford Summer School of Machine Learning  (May 7-10, July 6-14, 2024)

•