🌱Aadam's Garden

Search

Search IconIcon to open search

Deep Multi-task and Meta Learning - Autumn 2020

Last updated Jul 2, 2022

# Deep Multi-task and Meta Learning - Autumn 2020

Metadata

  • CiteKey:: chelseafinnDeepMultitaskMeta2022
  • Type:: presentation
  • Year:: 2022
  • Format:: PDF
  • Instructor:: Chelsea Finn

Abstract

Deep learning has achieved remarkable success in supervised and reinforcement learning problems including image classification, speech recognition, and game playing. These models are, however, to a large degree, specialized for the single task they are trained for. This course will cover the setting where there are multiple tasks to be solved. You will explore goal-conditioned reinforcement learning techniques that can increase learning speed of multiple tasks. You will discover how meta-learning methods can be used to learn new tasks quickly. You will learn how leverage the shared structure of a sequence of tasks to enable knowledge transfer. Through this course, you will develop and advance highly-sought after skills in the field of AI.

Files and Links

Tags and Collections

  • Keywords:: Courses, Deep Learning, Meta-Learning, Multi-task Deep Learning, Reinforcement Learning

# Annotations


# Notes