Deep Learning and Generative Models: Neural Network Foundations with PyTorch
Learn the mathematical and computational foundations of deep learning by building, training, and evaluating multilayer perceptrons in PyTorch. Part one in a five-part series, this online course in the Deep Learning and Generative Models program develops the experimental discipline needed to compare models and determine whether a change improves performance. These skills prepare you to build baseline models for classification and prediction tasks, such as categorizing observations or predicting outcomes from numerical data, and assess whether more complex models offer a meaningful improvement.
Course Information
Certificate Track
Learn for Free
About this Course
Neural networks begin with core building blocks: linear layers, nonlinear activation functions, and multilayer perceptrons (MLPs). See how these components transform data, then connect that process to the mathematics of learning by framing model training as an optimization problem, starting with linear least squares.
Depth and width shape what a network can represent, but capacity alone does not guarantee strong performance. Distinguish limited capacity from failed optimization or poor generalization. On the CIFAR-10 image dataset, use PyTorch to train an MLP, design an architecture within a fixed parameter budget, and test a regularization method against a shared baseline. Use the results to defend your architecture and training choices.
This is the first of five courses in the Deep Learning and Generative Models Program:
- Neural Network Foundations with PyTorch
- Training, Inference, and Model Evaluation
- Neural Network Architectures
- Representations and Self-Supervised Learning
- Diffusion and Autoregressive Models
What you'll learn
- Build multilayer perceptrons from linear layers and nonlinear activation functions
- Formulate learning as loss minimization over a hypothesis space
- Explain how network depth and width affect expressive capacity
- Distinguish limitations arising from approximation, optimization, and generalization
- Train and compare regularized MLPs on CIFAR-10 using PyTorch
How you'll learn
Real-World LearningLearn from MIT faculty and experts who ground their teaching in real-world cases rather than mathematical models, making the material approachable for all.
Practical ApplicationApply your new knowledge with hands-on, practical exercises drawn from healthcare, sports, finance, sustainability, and more.
- Learn On Demand
Access all course content online with complete flexibility to study at your own pace.
AI-Enabled SupportDeepen your understanding of the course material and get help on assignments from AskTIM, the AI assistant built by MIT researchers.
Stackable CredentialsEarn an MIT Open Learning certificate at each milestone—module, course, and program—demonstrating your AI expertise. Available in paid courses only.
Prerequisites
This program is designed for:
- Aspiring data scientists and machine learning engineers who want a structured introduction to deep learning
- Quantitative researchers who want to apply deep learning to technical or scientific problems
- Working professionals who need to evaluate, adapt, or deploy modern machine learning models
- Advanced undergraduate and graduate students in computer science, data science, statistics, mathematics, engineering, and related quantitative fields
- Continuing education learners seeking hands-on experience with deep learning and generative models
You should be comfortable programming in Python and working with linear algebra, multivariable calculus, including partial derivatives and the chain rule, and undergraduate probability and statistics. The Probability and Statistical Data Analysis series or equivalent coursework provides suitable preparation. No prior deep learning experience is required.
The labs run in Google Colab and are designed for its free GPU tier, so no local installation is required.
Meet your instructors
Phillip Isola
Associate Professor, MIT Electrical Engineering and Computer Science
Dr. Phillip Isola is an associate professor in MIT’s Department of Electrical Engineering and Computer Science. He earned his PhD in Brain and Cognitive Sciences at MIT, advised by Ted Adelson, and his undergraduate degree in computer science at Yale. His research spans computer vision, machine learning, robotics, and artificial intelligence, with contributions to generative AI and self-supervised representation learning. His group investigates how intelligence emerges and whether models trained on different data and modalities develop similar representations of the world. This work aims to uncover principles of human-like intelligence and inform the development of beneficial AI systems. Before joining MIT, he conducted postdoctoral research at UC Berkeley and worked as a visiting research scientist at OpenAI; his research experience also includes Google Research. His honors include Packard and Sloan fellowships, the PAMI Young Researcher Award, a Google Faculty Research Award, and Samsung’s AI Researcher of the Year Award. He received the Ruth and Joel Spira Award for Distinguished Teaching and has taught MIT courses in deep learning, computer vision, and embodied intelligence. Faculty website, official bio
