Notes
These are a collection of notes I've written in the past. Some are algorithms that I find interesting, some are mathematical theorems, and some are just books that I've read.
LLM Quiz
Questions on how large language models work, with solutions.
ML Implementations
Core ML building blocks written from scratch in NumPy and PyTorch.
LLM Concepts
How large language models are built, trained, served and tuned.
Probability Puzzles
Classic probability and logic puzzles with answers.
Probability Toolkit
Events, conditioning, expectation and counting.
Probability Distributions
Common distributions, limit theorems and inequalities.
Statistical Inference
Estimation, Bayesian updating and hypothesis testing.
Linear Regression
Least squares, its geometry, and regularized regression.
Linear Algebra
Eigenvalues, the SVD, norms and projections.
Matrix Calculus
Gradients of vectors and matrices, and backpropagation.
Optimization
Convexity, constraints and gradient-based training.
Information Theory
Entropy, cross-entropy and KL divergence in learning.
Stochastic Processes
Markov chains, martingales, Brownian motion and Itô.
Quantitative Finance
Risk, portfolios, CAPM, Kelly and option pricing.
Principles by Ray Dalio
An idea meritocracy that strives to achieve meaningful work and relationships.
12 Rules for Life
An antidote to chaos by psychologist Jordan Peterson.