Spring 2026
Machine Learning
University of Illinois Urbana-Champaign
Studied core ML methods and evaluation, focusing on how model assumptions, loss functions, and data properties drive performance.
- Supervised Learning
- Generalization
- Regularization
- Optimization
- Model Evaluation
Course Focus
Core machine-learning foundations: modeling choices, objective functions, training dynamics, and rigorous evaluation.
What I practiced
Translating problem statements into formal objectives and choosing models based on bias/variance and data constraints.
Reflection
Improved my ability to reason about why models fail (not just that they fail) and how to iterate systematically.