Introduction

• Conditional computation is a technique to increase a model’s capacity (without...
  

• The paper hypothesizes that main optimization challenges in multi-task learning arise because of...
  

Introduction

• The paper proposes GradNorm, a gradient normalization algorithm that improves multi-task...
  

Introduction

• Meta-learning techniques are shown to benefit from the use of deep...
  

Introduction

• The paper proposes Stochastic Weight Averaging (SWA) procedure for improving the...
  

Introduction

• The paper explores the connections between the concepts of a single...
  

Introduction

• The paper compares replay-based approaches with model-based approaches in Reinforcement Learning...
  

Introduction

• The paper proposed a Technique for improving the generalization ability of...
  

Introduction

• The paper considers learning scenarios where the training data is available...
  

Introduction

• The paper builds on the prior work on self-supervised contrastive learning...