How Machine Learning Models Learn

For curious beginners and early-career engineers: how models learn from data, from features, loss, and gradient descent to overfitting, honest evaluation, and the model families that lead to neural networks and today's language models.

4 sections ยท 10 lessons

Course outline

Learning From Data

  1. What It Means to Learn From Data
  2. Turning the World Into Features

How Training Works

  1. A Straight Line Is a Model
  2. Measuring Wrongness With Loss
  3. Gradient Descent: Training Step by Step
  4. Training a Mileage Model by Hand

Trusting a Model

  1. When a Model Memorizes Instead of Learns
  2. Testing a Model Honestly
  3. Probabilities, Thresholds, and the Accuracy Trap
  4. Should This Fraud Model Ship?

Model Families

  1. Neighbors, Trees, and Clusters
  2. From Neurons to Language Models

Start learning with Wondering