Skip to content

Deep Learning Workshop (Spring 2024)

Students may choose to complete this assignment individually or in teams of two. Each team will select a research paper from the list of papers below and prepare a presentation (maximum of 20 minutes) for the class. The presentation should demonstrate a thorough understanding of the chosen paper, highlighting key findings and technical concepts that connect to the topics covered in this course.

The final deliverable (via Gradescope) for each team is expected to be a set of slides in PDF format, focusing on the chosen topic.

Placeholder

Workshop

Galanti Louge, University Libraries, May 8th 12:30pm

Acknowledgement

This workshop is being sponsored by a TensorFlow and Google AI award to support machine learning courses and diversity programs.

Placeholder

12:30pm: Poster setup and Lunch/Refreshments

1pm: Poster session (Class Projects)

  • Dynamic Target Reach-to-Grasp: An Adaptive Approach Using Deep Reinforcement Learning (Ali, Shayan)
  • SENPAI: Student-Enhanced Natural language Processing AI (Demetrios, Sungyoun)
  • Large Text Summarization Using Label Classification and Llama3 (Abiral, Maedeh)
  • UFC Prediction with Neural Networks (Kevin, Jonathan)
  • Face Mask Detection (Ryan, Victoria)
  • Comparative Analysis of CNN, Zero-Shot CLIP, and ViT Models for Facial Emotion Recognition (Aidan, Rushad)
  • Mangrove Species Identification: The Case of Vision Transformers (Gyanko, Reuben)
  • Improving Earthquake Detection and Localization with CNNs (Zhangbao)
  • Deep Learning Fusion for Seafloor Pressure Prediction: Integrating CNN and LSTM Models (Quantao)
  • Decoding Crypto Volatility: Predictive Insights from LSTM-Based Deep Learning Models (Jonathan, Joshua)
  • Multimodal Early Fusion Deep Neural Net Using EEG-fNIRS Data for Classification of Auditory Processing in the Human Brain (Behtom)
  • Artificial Neural Networks in Electronic Circuit Design (Prinsca)

2:15pm: Paper presentations

  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, ICLR 2021 [PDF] (Jonathan, Joshua)

  • Masked Autoencoders Are Scalable Vision Learners, CVPR 2022 [PDF] (Ali, Shayan)

  • A ConvNet for the 2020s, CVPR 2022 [PDF] (Quantao, Zhangbao)

  • Segment Anything, Meta 2023 [PDF] (Gyanko, Reuben)

  • GradMax: Growing Neural Networks using Gradient Information, ICLR 2022 [PDF] (Abiral, Maedeh)

  • Gradient Descent: The Ultimate Optimizer, Neurips 2022 [PDF] (Aidan, Rushad)

3:45pm: Break

4pm: Paper presentations

  • Llama 2: Open Foundation and Fine-Tuned Chat Models, Meta 2023 [PDF] (Behtom)

  • Improving Text Embeddings with Large Language Models, ACL 2024 [PDF] (Demetrios, Sungyoun)

  • Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models, ICLR 2024 [PDF] (Prinsca)

  • Self-Rewarding Language Models, ICML 2024 [PDF] (Kevin, Jonathan)

  • Generative Agents: Interactive Simulacra of Human Behavior, UIST 2023 [PDF] (Ryan, Victoria)