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. 10
 Introduction Lecture01
2
Sept. 17
 Neural Networks Lecture02 Indicate your preferred papers for in-class presentation due Sept. 17
3
Sept. 24
 Convolutional Neural Networks Lecture03 Assignment 1 is posted on Brightspace. Due on Oct. 7. Tutorial1(PyTorch), Tutorial2(Python).
4
Oct. 1
 Recurrent Neural Networks Lecture04
5
Oct. 8
 Transformers, Generative Adversarial Networks (GANs) Lecture05 Project Proposal due.
6
Oct. 15
 Generative Adversarial Networks (GANs)

Lecture06

  • Image-to-image translation with conditional adversarial networks (Mostafa, Slides)
  • Progressive Growing of GANs for Improved Quality, Stability, and Variation (Xiao, Slides)
  • Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (Daniil, Slides)
  • A style-based generator architecture for generative adversarial networks (Nawab, Slides)
    		•  Assignment 2 is out. Due on Nov. 7
    7
    Oct. 22
    		 Few-shot Learning
  • Siamese neural networks for one-shot image recognition (Harikrishnan, Slides)
  • FaceNet: A Unified Embedding for Face Recognition and Clustering (Joshua, Slides)
  • Matching Networks for One Shot Learning (Ming, Slides)
  • Prototypical networks for few-shot learning (Khoa, Slides)
  • Learning to Compare : Relation Network for Few-Shot Learning (Anusha, Slides)
    		•
    Oct 29
    		 Fall Break No class
    8
    Nov. 5
    		 Few-shot Learning, Domain Adaptation, Zero-shot Learning
  • Few-Shot Unsupervised Image-to-Image Translation (Arunachalam, Slides)
  • Semantic Autoencoder for Zero-Shot Learning (Zhiyi, Slides)
  • Unsupervised Domain Adaptation for Zero-Shot Learning (Yanan, Slides)
    		•
    9
    Nov. 12
    		 Transfer Learning, Self-supervised Learning, Deep Clustering
  • Feature Generating Networks for Zero-Shot Learning (Mohammad Reza, Slides)
  • Learning without Forgetting (Moe, Slides)
  • Supervised Contrastive Learning (Shahriar, Slides)
  • Unsupervised deep embedding for clustering analysis (Slides)
  • Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering (Slides)
    		•
    10
    Nov. 19
    		 Interpretable AI
  • Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions (Esra, Slides)
  • This Looks Like That: Deep Learning for Interpretable Image Recognition (Victoria, Slides)
  • Why Should I Trust You? Explaining the Predictions of Any Classifier (Taoseef, Slides)
  • Cause and Effect: Concept-based Explanation of Neural Networks (Farukh, Slides)
    		•
    11
    Nov. 26
    		 Final Project Presentation Project presentation schedule is posted on Discord (see the Announcements channel)
    12
    Dec. 3
    		 Final Project Presentation Project presentation schedule is posted on Discord (see the Announcements channel)
    		Project Reports due on December 10