Papers I Read Notes and Summaries

Searching for Build Debt - Experiences Managing Technical Debt at Google

Introduction

  • The paper describes the efforts to control and repay the technical...


One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL

Introduction

  • Key idea: Practicing and remembering diverse solutions to a task can...


Learning Explanations That Are Hard To Vary

Introduction

  • The paper builds on the principle “good explanations are hard to vary”...

Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting

Introduction

  • The paper hypothesizes that catastrophic forgetting can happen if the model can...

A Foliated View of Transfer Learning

Introduction

  • The paper presents a formalism for transfer learning, offers a definition...


Harvest, Yield, and Scalable Tolerant Systems

Introduction

  • A classic paper that looks into strategies for scaling large systems...


MONet - Unsupervised Scene Decomposition and Representation

Introduction

  • The paper introduces Multi-Object Network (MONet) architecture that learns a modular...


Revisiting Fundamentals of Experience Replay

Introduction

  • The paper presents an extensive study of the effects of experience...


Deep Reinforcement Learning and the Deadly Triad

Introduction

  • The paper investigates the practical impact of the deadly triad (function...


Alpha Net--Adaptation with Composition in Classifier Space

Introduction

  • Common transfer learning method focuses on transferring knowledge in the model...