AUT LibraryAUT
View Item 
  •   Open Research
  • Faculties
  • Faculty of Culture and Society
  • School of Social Sciences and Public Policy
  • View Item
  •   Open Research
  • Faculties
  • Faculty of Culture and Society
  • School of Social Sciences and Public Policy
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Beyond Catastrophic Forgetting in Continual Learning: An Attempt with SVM

Benavides Prado, D
Thumbnail
View/Open
Conference Contribution (364.7Kb)
Permanent link
http://hdl.handle.net/10292/13829
Metadata
Show full metadata
Abstract
A big challenge in continual learning is avoiding catastrophically forgetting previously learned tasks. The possibility of improving existing knowledge whilst integrating new information has been much less explored. In this paper we describe a method that aims to improve the performance of previously learned tasks by refining their knowledge while new tasks are observed. Our method is an example of this ability in the context of Support Vector Machines for binary classification tasks, which encourages retention of existing knowledge whilst refining. Experiments with synthetic and real-world datasets show that the performance of these tasks can be continually improved by transferring selected knowledge, leading to the improvement on the performance of the learning system as a whole.
Date
July 18, 2020
Source
Proceedings of the 37 th International Conference on Machine Learning, Vienna, Austria, PMLR 108, 2020.
Item Type
Conference Contribution
Publisher
The International Conference on Machine Learning (ICML)
Publisher's Version
https://icml.cc/Conferences/2020/ScheduleMultitrack?event=5743
Rights Statement
Copyright 2020 by the author(s).

Contact Us
  • Admin

Hosted by Tuwhera, an initiative of the Auckland University of Technology Library

 

 

Browse

Open ResearchTitlesAuthorsDateSchool of Social Sciences and Public PolicyTitlesAuthorsDate

Alternative metrics

 

Statistics

For this itemFor all Open Research

Share

 
Follow @AUT_SC

Contact Us
  • Admin

Hosted by Tuwhera, an initiative of the Auckland University of Technology Library