Course Schedule & Materials

Time and Location: Monday, Wednesday 9:30AM - 10:50AM, Posner Hall 153. See Logistics for more details.


Date Event Description Materials Announcements
M; January 12 Lecture 1 Introduction to Deep Learning Readings: Bishop (Chapter 1, Chapter 3: 3.1-3.2), Deep Learning Book (Chapter 4, Chapter 5)
Links: Slides, Recording
W; January 14 Lecture 2 Continue Introduction to Deep Learning Readings: Bishop (Chapter 1, Chapter 3: 3.1-3.2), Deep Learning Book (Chapter 4, Chapter 5)
Links: Slides, Recording
F; January 16 - No Recitation -
M; January 19 Holiday MLK Jr. Day - No School -
W; January 21 Recitation 1 Distributions
Links: Slides, Recording
F; January 23 - No Recitation
M; January 26 Lecture 4 Neural Networks Part I Readings: Bishop (Chapter 5: 5.1-5.4), Deep Learning Book (Chapter 6)
Links: Slides, Recording
W; January 28 Lecture 5 Neural Networks Part II, ConvNets I Readings: Bishop (Chapter 5: 5.1-5.4), Deep Learning Book (Chapter 7)
Links: Slides (NN Part 2), Slides (Conv 1), Recording
HW1 Released
F; January 30 Recitation 2 Homework 1 Recitation Links: Slides, Recording
M; February 2 Lecture 6 Convolutional Neural Networks I and II Readings: Deep Learning Book (Chapter 9)
Links: Slides (Conv 1), Slides (Conv 2), Recording
W; February 4 Lecture 7 Graphical Models: Directed Models Links: Slides, Recording
M; February 9 Lecture 8 Undirected Graphical Models Readings: Deep Learning Book (Chapter 20.3)
Links: Slides, Recording
W; February 11 Lecture 9 Restricted Boltzmann Machines (RBMs) Readings: Deep Learning Book (Chapter 20.3)
Links: Slides, Recording
HW2 Released, HW1 Due
F; February 13 Recitation 4 Homework 2 Recitation Links: Slides, Recording
M; February 16 Lecture 10 Deep Belief Networks Links: Slides, Recording
W; February 18 NO CLASS Links: Slides, Recording
F; February 20 Recitation: PyTorch and AWS Links: Slides, Recording
M; February 23 Lecture 11 Autoencoders Readings: Deep Learning Book (Chapter 10 and Chapter 12: 12.4)
Links: Autoencoder Slides, Midterm Review Slides
W; February 25 Lecture 12 Language Modeling, Project Proposal Due Links: Slides, Recording
F; February 27 Midterm exam
M; March 2 NO CLASS Spring Break -
W; March 4 NO CLASS Spring Break -
F; March 6 NO CLASS Spring Break -
M; March 9 Lecture 13 Sequence Models, RNNs Links: Slides 1,Slides 2, Recording HW2 Due,midterm review, midway project proposal
W; March 11 Lecture 14 Sequence Models, Transformers Links: Slides, Recording HW3 Released
F; March 13 Recitation 5 Recitation: Homework 3 Links: Slides, Recording
M; March 16 Lecture 15 Variational Inference Links: Slides, Recording
W; March 18 Lecture 16 Variational Autoencoders Links: Slides, Recording Midway Report - 3/18
F; March 20 - No recitation -
M; March 23 Lecture 17 Markov Chain Monte Carlo Links: Slides, Recording
W; March 25 Lecture 18 Multimodal Language Models Links: Slides, Recording
F; March 27 - No recitation -
M; March 30 Lecture 19 Diffusion Models Links: Slides, Recording HW4 Released, HW3 Due
W; April 1 Lecture 20 No lecture Links: Slides, Recording
F; April 3 Recitation 6 Recitation: HW 4 Links: Slides, Recording
M; April 6 Lecture 20 Generative Adversarial Networks / Normalizing Flows Links: Slides, Recording
W; April 8 Lecture 21 LLM AI Agents Links: Slides, Recording
F; April 10 NO CLASS Carnival - No Class -
M; April 13 Lecture 22 Embodied AI: Language and Perception Links: Slides, Recording
W; April 15 Lecture 23 Integrating Domain Knowledge Into Deep Learning Links: Slides, Recording
F; April 17 - No Recitation -
M; April 20 Lecture 24 Introduction to Reinforcement Learning Links: Slides, Recording HW4 Due
W; April 22 Lecture 26 Generative Models for Data Augmentation Links: Slides, Recording Final Project Due

* all announcement dates are tentative and subject to change

Resources

Books Additional references

Diversity Statement

We must treat every individual with respect. We are diverse in many ways, and this diversity is fundamental to building and maintaining an equitable and inclusive campus community. Diversity can refer to multiple ways that we identify ourselves, including but not limited to race, color, national origin, language, sex, disability, age, sexual orientation, gender identity, religion, creed, ancestry, belief, veteran status, or genetic information. Each of these diverse identities, along with many others not mentioned here, shape the perspectives our students, faculty, and staff bring to our campus. We, at CMU, will work to promote diversity, equity and inclusion not only because diversity fuels excellence and innovation, but because we want to pursue justice. We acknowledge our imperfections while we also fully commit to the work, inside and outside of our classrooms, of building and sustaining a campus community that increasingly embraces these core values.

Each of us is responsible for creating a safer, more inclusive environment. Unfortunately, incidents of bias or discrimination do occur, whether intentional or unintentional. They contribute to creating an unwelcoming environment for individuals and groups at the university. Therefore, the university encourages anyone who experiences or observes unfair or hostile treatment on the basis of identity to speak out for justice and support, within the moment of the incident or after the incident has passed. Anyone can share these experiences using the following resources:

All reports will be documented and deliberated to determine if there should be any following actions. Regardless of incident type, the university will use all shared experiences to transform our campus climate to be more equitable and just.