Schedule »

Week Content PDF
W01 Class Intro & Planning
W02 Representation Learning
 02-1
  Structured Probabilistic Models
 02-2
  Monte Carlo Methods
 02-3
W03 Confronting the Partition Function
 03-1
  Approximate Inference
 03-2
  Deep Generative Models I
 03-3
W04 Deep Generative Models II
 04-1
  Regularization in Deep Learning I
 04-2
  Deep Generative Models II
 04-3
W05 Training DNNs I
 05-1
  Training DNNs II
 05-2
W06 Model Pre-Training, Self-Supervised Learning : Key Models & Methods
 06-1
  Model Pre-Training, Self-Supervised Learning : Analysis Papers & Model Understanding
 06-2
  Model Pre-Training, Self-Supervised Learning : Recent Advances
 06-3
W07 Multi-Task Learning for NLP
 07-1
  Advances in Transfer Learning for NLP: Domain Adaptation
 07-2
  Advances in Transfer Learning for NLP: Cross-Lingual Transfer
 07-3
W08 Mid-term Presentation
W09 Overview of Few-Shot Learning
 09-1
  Overview of Meta Learning
 09-2
  Few-Shot & Meta Learning in NLP
 09-3
W10 Techniques for Understanding Model Component / Behaviours
 10-1
  Adversarial Learning / Examples
 10-2
  Interpretable Model Architectures
 10-3
W11 Question Answering & Reading Comprehension : Dataset & Analysis Papers
 11-1
  Question Answering & Reading Comprehension : Models I
 11-2
  Question Answering & Reading Comprehension : Models II
 11-3
W12 Commonsense Reasoning & Inference: Datasets & Knowledge Acquisition
 12-1
  Commonsense Reasoning & Inference: Models I
 12-2
  Commonsense Reasoning & Inference: Datasets & Models II
 12-3
W13 Multi-Model Learning: Datasets, Resources & Analysis Work
  Multi-Model Learning: Models
W14 Final Presentation