Spring 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) / 11:00am–12:20pm (Section B) · Coding labs & recitations mostly Fridays
Lectures
27
Homeworks
9
Quizzes
3
Exams
3
Instructors
Course Modules
Classification & Regression
Course Overview
Machine Learning as Function Approximation
Decision Trees
Decision Tree Properties and Hyperparameters
k-Nearest Neighbor and Model Selection
Linear Models
Perceptron
Linear Regression
Optimization for ML
Stochastic Gradient Descent / Logistic Regression
Feature Engineering / Regularization
Neural Networks
Neural Networks
Backpropagation I
Backpropagation II
Societal Impacts
Societal Impacts of ML
Learning Theory
PAC learning
PAC Learning / MLE & MAP
Deep Learning
MLE & MAP / CNNs and RNNs
RNN-LMs and Transformers-LMs
Transformers, AutoDiff, Pre-training, Fine-Tuning
Reinforcement Learning
In-context Learning / Reinforcement Learning: MDPs
Reinforcement Learning: Value/Policy Iteration
Reinforcement Learning: Policy Gradient / Deep RL
Learning Paradigms
Recommender Systems
Ensemble Methods: Boosting & Bagging
K-Means / Dimensionality Reduction: PCA
Special Topics: Coding Agents / Significance Testing for ML
Special Topics: Generative Models for Vision
Announcements
Welcome to 10-301/601!
1/13/2026
Lectures begin the first week of the semester. Please read the Syllabus and set up Gradescope.
Fall 2026 Information
1/12/2026
For information about 10-301/601 in Fall 2026, click here!