Probability - Math for Machine Learning
In this video, W&B's Deep Learning Educator Charles Frye covers the core ideas from probability that you need in order to do machine learning. In particular, we'll see why mathematically rigorous probability theory is so challenging, and then go over why negative logarithms of probabilities, aka "surprises", show up so often in machine learning. Slides here: http://wandb.me/m4ml-probability Exercise notebooks here: https://github.com/wandb/edu/tree/mai... Check out the other Math4ML videos here: http://wandb.me/m4ml-videos 0:00 Introduction 1:45 Probability is subtle 7:45 Overview of takeaways 8:47 Probability is like mass 17:51 Surprises show up more often in ML 21:46 Surprises give rise to loss functions 24:31 Surprises are better than densities 33:35 Gaussians unite probability and linear algebra 39:57 Summary of the Math4ML ideas 41:40 Additional resources on Math4ML

Math4ML Exercises: Probability

Probability Must-Knows for Machine Learning | Math for ML (Part 1)

The Key Equation Behind Probability

Probability and Statistics: Overview

The Strange Math That Predicts (Almost) Anything

The better way to do statistics | Bayesian #1

The Elegant Math Behind Machine Learning

Probability Top 10 Must Knows (ultimate study guide)

Reinventing Entropy | Compression is Intelligence Part 1

1. Introduction to Statistics

Why is probability important to machine learning?

Bayes theorem, the geometry of changing beliefs

Stanford CS109 Probability for Computer Scientists I Counting I 2022 I Lecture 1

The Bayesian Trap

Linear Algebra - Math for Machine Learning

Binomial distributions | Probabilities of probabilities, part 1

Is the AI Boom About to COLLAPSE?

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

Something is jamming GPS over Europe. Here's what we found

