Advanced-Topics-in-Machine-Learning-and-Data-Science

Objective

In this seminar, recent papers of the machine learning and data science literature are presented and discussed. Possible topics cover statistical models, machine learning algorithms, and their applications.

The seminar “Advanced Topics in Machine Learning and Data Science” familiarizes students with recent developments in machine learning and data science. Recently published articles, as well as influential papers, have to be presented and critically reviewed. The students will learn how to structure a scientific presentation, which covers the motivation, key ideas and main results of a scientific paper. An important goal of the seminar presentation is to summarize the essential ideas of the paper in sufficient depth for the audience to be able to follow its main conclusion, especially why the article is (or is not) worth attention. The presentation style will play an important role and should reach the level of professional scientific presentations.

Contact:

Fernando Perez-Cruz

Office OAT

Lectures:

Wednesday 16:00 – 18:00 LFW E13

Schedule:

• February 21st: [Introduction]
• February 28th: No lecture
• March 6th:
  • Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning by Simone Libutti.
  • Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness by Nicolas Blumer.
• March 13th:
  • Attention Is All You Need by Kerem Gura.
  • BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Rene Caky
• March 20th:
  • Does data interpolation contradict statistical optimality? by Omar Mezghani
  • In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning by Steve Rhyner.
• March 27th:
  • High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion) by Marcus Nielsen.
  • Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models by Gegor Zunic.
• April 3rd: (Easter): No lecture
• April 10th:
  • Emergent Abilities of Large Language Models by Cyrill Püntener
  • Are Emergent Abilities of Large Language Models a Mirage? by Chao Chen
• April 17th:
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models by Michael Ungersböck.
  • Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective
  • NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis by Nazar Puriy.
• April 24th:
  • Denoising Diffusion Probabilistic Models by Luka Secilmis.
  • Neural Tangent Kernel: Convergence and Generalization in Neural Networks by Lukas Häuser.
• May 1st: No lecture
• May 8th:
  • MLP-Mixer: An all-MLP Architecture for Vision by Hector Maeso Garcia.
  • Pay attention to MLPs by Sascha Tran.
• May 15th:
  • Continuous Deep Q-Learning with Model-based Acceleration by Frederieke Lohmann.
  • Supervised Contrastive Learning by Andrei Arnautu
• May 22nd:
  • Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data by Elena Bösch
  • AI And The Limits Of Language by Zdenek Snajdr
• May 29th:
  • Cognitive Architectures for Language Agents by Yanick Zengaffinen
  • A Path Towards Autonomous Machine Intelligence by Mamoun Chami