Some of Machine Learning Resources
Explore curated learning paths from fundamentals to advanced topics. Each resource connects to interactive Confluence tools where you can practice and experiment with real algorithms.
Linear Algebra
beginnerFundamentalsVectors, matrices, and transformations are the language of ML. Every model internally uses linear algebra for computation.
Statistics & Probability
beginnerFundamentalsThe mathematical foundation of machine learning. Understanding distributions, hypothesis testing, and Bayesian thinking is essential for interpreting model results.
Optimization
intermediateFundamentalsHow models learn. Gradient descent, loss functions, and convergence are the mechanisms behind training.
Feature Engineering
intermediatePracticeTransforming raw data into useful features. Often more impactful than algorithm choice.
Evaluation
intermediatePracticeMeasuring model performance correctly. Understanding metrics prevents overfitting to the wrong goal.
Model Selection
intermediatePracticeChoosing the right algorithm and tuning it. No single algorithm works best for everything.
Deployment
advancedAdvancedTaking models to production. Serialization, APIs, monitoring, and maintaining models over time.
Recommended Learning Platforms
beginnerCurated collection of documentation, interactive courses, and YouTube channels for continuous learning in machine learning and data science.