• Home
  • Research
  • AI Notes
  • Coaching

AI Notes

Welcome to my AI Notes - a collection of technical articles where I document concepts, papers, and insights as I learn and explore the field of Artificial Intelligence and Machine Learning.

This is a work in progress, evolving between individual notes and potentially a more structured book format.


Stats and Machine Learning

  • Biased and unbiased estimators
  • La maldición de la multidimensionalidad
  • Importance Sampling
  • Metropolis-Hastings Algorithm
  • Gibbs Sampling
  • Variational Inference
  • Variational Autoencoders (VAE)
  • Non-negative Matrix Factorization (Lee and Seung algorithm)
  • The Chinese Restaurant Process
  • Generating distributions with the Stick Breaking version of the Dirichlet Process

Large Language Models

  • Tokenization
  • Attention Mechanisms
  • Proximal Policy Optimization (PPO)
  • Direct Preference Optimization (DPO)
  • Group Relative Policy Optimization (GRPO)
  • Reinforcement Learning from AI Feedback (RLAIF)
  • Reinforcement Learning from Visual Feedback (RLVF)

Hands-on

  • Fine-tuning an LLM for Meal Planning

Agents

  • What is an Agent?
  • Structured Outputs and Tool Calling
  • Agent Design Patterns
  • On Training Agents

Paper Reviews


Miscellaneous

  • Introduction to Stats and Machine Learning
  • Expectation-Maximization Algorithm
  • Introduction to Large Language Models
  • Introduction to Agents
  • Introduction to Paper Reviews