Schedule (tentative)
Note that the schedule is tentative, and will change depending on how slow / fast we are able to go. In particular, assignment release and due dates, quiz times, and project milestones shown here are subject to changes unless they have actually been released through the respective links: assignments, project, exams.
Recommended Textbooks
PML: Probabilistic Machine Learning: An Introduction by Kevin Patrick Murphy (MIT Press, March 2022, Available online)
Bishop: Deep Learning: Foundation and Concepts by Chris Bishop with Hugh Bishop (Springer 2024, Available online)
| Date | Topic | Slides | Readings | Assignments |
| 8 / 27 | Introduction | Python / numpy tutorial | ||
| Machine Learning Basics | ||||
| 8 / 29 | k Nearest Neighbors | PDF1, PDF2 | PML 1, 16.1 | |
| 9 / 3 | Linear Classifiers | PDF, PPTX | PML 7, PML 10.1, 10.2 | Assignment 1 Sep 4 – Sep 18 |
| 9 / 5 | Linear Classifiers | ^ | PML 7, PML 10.1, PML 10.2 | |
| 9 / 10 | Linear Classifiers | ^ | PML 7, PML 10.1, PML 10.2 | |
| 9 / 12 | Feature Design, Non-linear Classifiers Classifier Complxity, Bias-Variance | PDF, PPTX | Digit Case Study, PML 17.3, 4.7.6 | |
| Neural Networks Basics | ||||
| 9 / 17 | Back-propagation | PDF, PPTX | PML 13.3 | Assignment 2 Sep 18 – Oct 9 |
| 9 / 19 | Training Neural Networks | PDF, PPTX | PML 13.4, 13.5 | |
| 9 / 24 | Training Neural Networks | ^ | ||
| 9 / 26 | Exam Review | PPTX, PDF | CBTF Exam 1 Sep 30 – Oct 2 | |
| Neural Networks for Images | ||||
| 10 / 1 | Convolutions, Max Pooling | PDF, PPTX | PML 14.2 | |
| 10 / 3 | AlexNet and FineTuning | PDF, PPTX | PML 14.2 | |
| 10 / 8 | Residual Networks, Other CNNs | PML 14.3.2 | Assignment 3 Oct 9 – Oct 23 | |
| 10 / 10 | Residual Networks, Other CNNs | ^ | PML 14.3 | IEF |
| 10 / 15 | Attention | ^ | PML 14.3, ViT, VPT | Project Proposal Oct 16 |
| 10 / 17 | How to Train your Network? (Aditya Prakash) | |||
| 10 / 22 | Object Detection | RCNN, Fast RCNN, Faster RCNN | ||
| 10 / 24 | Object Detection | ^ | FPN, Mask RCNN, RetinaNet, Swin, ViTDet, DETR | Assignment 4 Oct 23 – Nov 20 |
| 10 / 29 | Dense Prediction | PDF, PPTX | FCN, UNET, SAM | |
| 10 / 31 | Sequence Modelling | |||
| 11 / 5 | Sequence Modelling | ^ | Optional: S4, Mamba, TTT | |
| 11 / 7 | Image Generation, Score Matching | PDF1 | NCNS | Assignment 5 Nov 13 – Dec 4 |
| 11 / 12 | Score Matching | PDF2 | ||
| 11 / 14 | Diffusion Models | PDF3 | Latent Diffusion, VQ VAE, DDIM, Conditioning, Guidance, Fourier Features | |
| 11 / 19 | Diffusion Models | |||
| 11 / 21 | Variational Auto Encoders | PDF4.1 PDF4.2 | VAEs VAEs to Diffusion Blog | |
| 11 / 26 | No Class (Fall Break) | |||
| 11 / 28 | No Class (Fall Break) | |||
| 12 / 3 | VAEs | |||
| 12 / 5 | Generative Adversarial Networks | PDF5 | ||
| 12 / 10 | Exam Review | Compute Survey Flex | ||
| Projects Due Dec 10 | ||||
| CBTF Final Exam Dec 11 – Dec 15 | ||||
| Self supervision | PDF, PPTX | MAE | ||
| Neural Radiance Fields (NeRFs) | NeRF, Instant NGP | |||
| Vision and Language Models | Molmo and PixMo | |||
| Bias in AI | Good starting points: Datasheets for Datasets, Model Cards for Model Reporting |
