10-301 / 10-601Introduction to Machine Learning

Fall 2026 · Carnegie Mellon University

Introduction to Machine Learning

10-301 / 10-601

A thorough grounding in the methodologies, mathematics, and algorithms of modern machine learning.

MWF 9:30–10:50am (Section A, DH 2315) / 11:00am–12:20pm (Section B, GHC 4401) · Coding labs & recitations mostly Fridays

Lectures

26

Homeworks

9

Programming Tests

3

Exams

3

Instructors

Matt Gormley

Bryan Wilder

Example slides

The recipe for machine learning

Backpropagation through a computation graph

A convolutional neural network

A separating hyperplane

Naive Bayes

A non-convex optimization landscape

Course Modules

About

The Course

Classification & Regression

Course Overview

Course Overview

Lecture 1: Course Overview

Machine Learning as Function Approximation

Machine Learning as Function Approximation

Decision Trees

Decision Trees

Decision Tree Properties and Hyperparameters

Decision Tree Properties and Hyperparameters

k-Nearest Neighbor and Model Selection

k-Nearest Neighbor and Model Selection

Lecture 5: k-Nearest Neighbor and Model Selection

Linear Models

Perceptron

Perceptron

Lecture 6: Perceptron

Linear Regression

Linear Regression

Optimization for ML

Optimization for ML

Stochastic Gradient Descent / Logistic Regression

Stochastic Gradient Descent / Logistic Regression

Lecture 9: Stochastic Gradient Descent / Logistic Regression

Feature Engineering / Regularization

Feature Engineering / Regularization

Neural Networks

Neural Networks

Neural Networks

Backpropagation I

Backpropagation I

Backpropagation II

Backpropagation II

Societal Impacts

Societal Impacts of ML (Evaluation)

Societal Impacts of ML (Evaluation)

Learning Theory

PAC learning

PAC learning

Lecture 15: PAC learning

PAC Learning / MLE & MAP

PAC Learning / MLE & MAP

Lecture 16: PAC Learning / MLE & MAP

Deep Learning

MLE & MAP / CNNs and RNNs

MLE & MAP / CNNs and RNNs

RNN-LMs and Transformers-LMs

RNN-LMs and Transformers-LMs

Transformers, AutoDiff, Pre-training, Fine-Tuning

Transformers, AutoDiff, Pre-training, Fine-Tuning

Reinforcement Learning

In-context Learning / Reinforcement Learning: MDPs

In-context Learning / Reinforcement Learning: MDPs

Reinforcement Learning: Core Algorithms

Reinforcement Learning: Core Algorithms

Lecture 21: Reinforcement Learning: Core Algorithms

Reinforcement Learning: Policy Gradient / Deep RL

Reinforcement Learning: Policy Gradient / Deep RL

Learning Paradigms

Unsupervised Learning: Autoencoders / PCA / K-Means

Unsupervised Learning: Autoencoders / PCA / K-Means

Lecture 23: Unsupervised Learning: Autoencoders / PCA / K-Means

Recommender Systems / Matrix Factorization

Recommender Systems / Matrix Factorization

Lecture 24: Recommender Systems / Matrix Factorization

Ensemble Methods: Boosting & Bagging

Ensemble Methods: Boosting & Bagging

Special Topics: Coding Agents / Generative Models for Vision

Special Topics: Coding Agents / Generative Models for Vision