Mathematics & Statistics for ML — Machine Learning Roadmap
The mathematical intuition behind why machine learning algorithms actually work
Steps in Mathematics & Statistics for ML
- Linear Algebra Essentials — beginner · Vectors, matrices, matrix multiplication and how data is represented numerically
- Calculus Essentials — beginner · Derivatives, gradients and the chain rule that underlie model training
- Probability Fundamentals — beginner · Random variables, conditional probability and independence
- Descriptive Statistics — beginner · Mean, median, variance, standard deviation and summarizing a dataset
- Probability Distributions — beginner · Normal, binomial and other common distributions and where they show up in data
- Hypothesis Testing & Confidence Intervals — beginner · p-values, significance and drawing conclusions from sample data
- Bayesian Thinking Basics — beginner · Updating beliefs with evidence using Bayes' theorem
- Optimization Basics (Gradient Descent Intuition) — beginner · The core idea of iteratively improving a model by following the gradient downhill
Part of
- Machine Learning roadmap — the full learning path