| 04/02/24 |
Intro to Large Language & Vision Models What is AI and why pursue it Weak vs Strong AI Intro to Large Models for vision and language AI4Science applications Current LLVMs and failures Class overview, homeworks, grading policy |
 Pietro  Georgia |
Slides - Part A by Pietro: pdf Slides - Part B by Georgia: pdf |
| 04/04/24 |
Brief Recap on MLPs Definition of MLPs Backpropagation Stochastic Gradient Descent Momentum (paper) Adam (paper) |
Pietro |
Pietro's slides: pdf Assignment 1: main & code. |
| 04/09/24 |
Recurrent Neural Networks Word Embddings Hidden Markov Models (HMMs) Sequence to Sequence (paper) Attention (paper) |
 Rogério |
Rogério's slides: pdf |
| 04/11/24 |
Convolutional Neural Networks CNNs (LeNet, AlexNet) Residual Nets (paper) U-Net (paper) Normalization, Dropout |
Georgia |
Georgia's slides: pdf |
| 04/16/24 |
Transformers I: Self-Attention Attention is all you need (paper) ViT (paper) |
Georgia |
Georgia's slides: pdf |
| 04/18/24 |
Guest Lecture: Towards Better Understanding of Representation Collapsing in Representation Learning |
|
Yuandong's slides: pdf Assignment 2: main &code &code starter for ResNet & code starter for ViT |
| 04/23/24 |
Transformers II: Encoder |
Georgia |
Georgia's slides: pdf |
| 04/25/24 |
Transformers III: Decoder |
Georgia |
Georgia's slides: pdf |
| 04/30/24 |
Self-Supervised Learning with Large Models SimCLR (paper) BERT (paper) MAE (paper) DINO (paper) DINOv2 (paper) |
Pietro |
Pietro's slides: pdf |
| 05/02/24 |
Object Recognition at Scale - Part A Faster R-CNN (paper) Mask R-CNN (paper) ViTDet (paper) DETR (paper) |
Georgia |
Georgia's slides: pdf Assignment 3: main,code,colab1,colab2 |
| 05/07/24 |
Object Recognition at Scale - Part B Faster R-CNN (paper) Mask R-CNN (paper) ViTDet (paper) DETR (paper) |
Georgia |
Georgia's slides: pdf |
| 05/09/24 |
Generative Models - Part A Intro to Generative Models Autoregresive Models GPT (GPT,GPT2, GPT3) PixelCNN (paper) WaveNet (paper) |
Georgia |
Georgia's slides: pdf |
| 05/14/24 |
Generative Models - Part B Variational Autoencoders Tutorial on VAEs (paper) VQ-VAE (paper) |
Georgia |
Georgia's slides: pdf |
| 05/16/24 |
Generative Models - Part C Diffusion Models DDPMs (paper) Denoising Score Matching (paper) |
Georgia |
Georgia's slides: pdf |
| 05/21/24 |
Generative Models - Part D Generative Adversarial Networks (paper) |
Pietro |
Pietro's slides: pdf |
| 05/23/24 |
Alignment Intro to RL REINFORCE, PPO InstructGPT (paper) |
Pietro |
Pietro's slides: pdf |
| 05/28/24 |
Responsible AI |
Pietro |
Pietro's slides: pdf |
| 05/30/24 |
Vision & Language CLIP (paper) |
Georgia |
Georgia's slides: pdf |