Patterns, Predictions, and Actions Live Blog

2

I’ll be live blogging my graduate course on machine learning this semester (Fall 2023). The course is based on the text Patterns, Predictions, and Actions by Moritz Hardt and myself.

A Table of Contents

Part I: Prediction

  1. Lecture 1: Introduction

    1. Part 1: Patterns, Predictions, and AGI

    2. Part 2: Fact, Fiction, and Forecast

    3. Part 3: We are more than players

  2. Lecture 2: What is machine learning?

    1. Rise of the Spreadsheets

  3. Lecture 3: The Perceptron

    1. Part 1: Yoshimi Battles The Perceptrons

    2. Part 2: The war of symbolic aggression

  4. Lecture 4: Optimization

    1. Part 1: 7 minute Opts

    2. Part 2: Rigor Vs. Github Descent

  5. Lecture 5: Sequential Prediction

    1. Regretfully Yours

  6. Lecture 6: Generalization

    1. Part 1: Generally speaking when god plays dice

    2. Part 2: Three paths to generalization

    3. Part 3: I don't know what I've been trying to prove

    4. Segue: Features of the foundations of machine learning

  7. Lecture 7: Features

    1. Hidden foundations

  8. Lecture 8: Nonlinear Prediction Functions

    1. The maddening nonlinear multiverse

    2. It’s not a trick…

  9. Lecture 9: Neural Networks

    1. No one knows how the brain works

    2. The Deep Optimization Cookbook

  10. Lecture 10: Generalization in Practice

    1. My Mathematical Mind

    2. Apostasy or reformation

  11. Lecture 11: Datasets

    1. The Department of Frictionless Reproducibility

    2. Revisiting Highleyman's Data

    3. The Data Winter

  12. Lecture 12: Internal and External Validity

    1. You got a 9 to 5, so I'll take the night shift

  13. Lecture 13: Elementary Policy Optimization

    1. The inductive leap

    2. A game of chance to you to him is one of real skill

    3. The fake rigor of the mighty dollar

  14. Lecture 14: Hypothesis Testing

    1. Look before you leap

  15. Lecture 15: Algorithmic Fairness

    1. Can you please everyone?

  16. Lecture 16: Randomized Controlled Experiments

    1. The impact of actions

    2. The national academy of spaghetti on the wall

  17. Lecture 17: Causal Inference

    1. Three Causal Graphs

    2. Fractions or the laws of nature?

  18. Lecture 18: Causal Inference in the Wild

    1. All published results are wrong, but some are useful

    2. We need an instrument to take a measurement

  19. Lecture 19: Stochastic Optimization and Policy Optimization

    1. Policy Phylogenesis

    2. Some simple plans

  20. Lecture 20: Regret minimization and the multi-armed bandit

    1. Extremely Online

    2. Quantifying those unknown unknowns

  21. Lecture 21: Decision making in dynamical systems

    1. Architectural Theories

    2. Integral Action

  22. Lecture 22: Algorithms for decision making in dynamical systems

    1. Greetings Professor Falken

    2. Feedback on feedback

  23. Lecture 23: Reinforcement learning

    1. Cool Kids Keep

  24. Lecture 24: Machine Learning and Computer Gameplay

    1. A Strange Game

    2. The only winning move

  25. Epilogue

    1. To do the mindblowing

    2. Yogi Berra in everything