吴正龙’s machine-learning Bookmarks

The reliable performance of on-policy training with the cost-efficiency of a dense reward signal.

A practical breakdown of Gradient Descent, the backbone of ML optimization, with step-by-step examples and visualizations.

Machine learning interview prep materials representing the collective wisdom of many people who have sat on both sides of the table, and who have spent a lot of time thinking about the hiring process.

Practical patterns for integrating large language models (LLMs) into real systems and products. Overview of seven key patterns: evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.

Different angle on attention mechanism to help build further intuition. Intended for people who have read the "Attention is All You Need" paper and have a basic understanding of how attention works.

Visual walkthrough of how various gradient descent methods work. Assumes basic familiarity of why and how gradient descent is used in machine learning.

Overview of different types of transfer learning techniques, and how they can be used to transfer knowledge to a different task, language or domain.

A whirlwind tour of PyTorch's internals, covering tensors, autograd, and the overall structure of the project. Meant for aspiring OSS contributors.

BERT was a model that broke several records for how well models could handle language-based tasks.

Overview of transfer learning and discussion of practical applications and methods.