DeepAI AI Chat
Log In Sign Up

Learning to Transfer: A Foliated Theory

by   Janith Petangoda, et al.
The University of Sheffield
Imperial College London

Learning to transfer considers learning solutions to tasks in a such way that relevant knowledge can be transferred from known task solutions to new, related tasks. This is important for general learning, as well as for improving the efficiency of the learning process. While techniques for learning to transfer have been studied experimentally, we still lack a foundational description of the problem that exposes what related tasks are, and how relationships between tasks can be exploited constructively. In this work, we introduce a framework using the differential geometric theory of foliations that provides such a foundation.


page 1

page 2

page 3

page 4


A Foliated View of Transfer Learning

Transfer learning considers a learning process where a new task is solve...

A Theory for Knowledge Transfer in Continual Learning

Continual learning of a stream of tasks is an active area in deep neural...

Importance Weighted Transfer of Samples in Reinforcement Learning

We consider the transfer of experience samples (i.e., tuples < s, a, s',...

Low-Cost Transfer Learning of Face Tasks

Do we know what the different filters of a face network represent? Can w...

Learning Across Tasks and Domains

Recent works have proven that many relevant visual tasks are closely rel...

Framing Visual Musicology through Methodology Transfer

In this position paper, we frame the field of Visual Musicology by provi...

Meta-Learning with MAML on Trees

In meta-learning, the knowledge learned from previous tasks is transferr...