CS-22828 Machine learning theory Course material

Noise Injection Techniques provides a comprehensive exploration of methods to make machine learning models more robust to real-world bad data. This repository explains and demonstrates Gaussian noise, dropout, mixup, masking, adversarial noise, and label smoothing, with intuitive explanations, theory, and practical code examples.

Notes on papers and books in ML theory and optimization. Structured via GitHub Issues for long-term searchability.

Code for my undergraduate thesis "An Investigation into Energy Minimization Properties of MLP Features in LLMs"