Schedule

*This schedule is evolving and will change based on your interests and how the class is progressing. See here for a list of topics and related papers.
Lec. Date Topic Slides Deadlines
1
Sept. 12
 Introduction Lecture01
2
Sept. 19
 Neural Networks Lecture02 Indicate your preferred papers for in-class presentation due Sept. 18
3
Sept. 26
 Convolutional Neural Networks Lecture03 Assignment 1 is posted on Brightspace. Due on Oct. 11. Tutorial1(PyTorch), Tutorial2(Python).
4
Oct. 3
 Recurrent Neural Networks Lecture04
Oct. 10
 Thanksgiving Day No Class
5
Oct. 11
 Language Models, Transformers, Generative Adversarial Networks Lecture05 Project Proposal due Oct. 12.
Oct. 17
 No Class Assignment 2 is out. Due on Nov. 16
Oct. 24
 Fall Break No Class
6
Oct 31
 Generative Adversarial Networks (GANs)

Lecture06

  • BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (Andre, Slides)
  • Image-to-image translation with conditional adversarial networks (Rodrigo, Slides)
  • Unpaired image-to-image translation using cycle-consistent adversarial networks (Aagyapal, Slides)
  • A style-based generator architecture for generative adversarial networks (Taoyu, Slides)
  • Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization (Ali, Slides)
    		•
    7
    Nov. 7
    		 Few-shot Learning
  • FaceNet: A Unified Embedding for Face Recognition and Clustering (Heny, Slides)
  • Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (Arka, Slides)
  • Matching Networks for One Shot Learning (Rongchen, Slides)
  • Prototypical networks for few-shot learning (Booshra, Slides)
  • Learning to compare: Relation network for few-shot learning (Omar, Slides)
    		•
    8
    Nov. 14
    		 Zero-shot Learning, Transfer Learning, Self-supervised Learning
  • Semantic Autoencoder for Zero-Shot Learning (Rakshil, Slides)
  • Learning without Forgetting (Projna, Slides)
  • A Simple Framework for Contrastive Learning of Visual Representations (Zhikun, Slides)
  • Momentum Contrast for Unsupervised Visual Representation Learning (Cristopher, Slides)
    		•
    9
    Nov. 21
    		 Deep Clustering, Interpretable AI
  • Unsupervised deep embedding for clustering analysis (Slides)
  • Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering (Slides)
  • SpectralNet: Spectral Clustering using Deep Neural Networks (Ahmed, Slides)
  • Why Should I Trust You?: Explaining the Predictions of Any Classifier (Yitong, Slides)
  • A Unified Approach to Interpreting Model Predictions (Colin, Slides)
    		•
    10
    Nov. 28
    		 Interpretable AI
  • Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (Sourav , Slides)
  • Cause and Effect: Hierarchical Concept-based Explanation of Neural Networks (Mitchell, Slides)
  • Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions (Yiqun, Slides)
  • This Looks Like That: Deep Learning for Interpretable Image Recognition (Sadid, Slides)
    		•
    11
    Dec. 5
    		 Final Project Presentations Project presentation schedule is posted on Discord (see the General channel)
    12
    Dec. 9
    		 Final Project Presentations Project presentation schedule is posted on Discord (see the General channel)
    		Project Reports due on December 10 extended until Dec 15