Continual Learning through Evolvable Neural Turing Machines

Research output: Contribution to conference - NOT published in proceeding or journalPaperResearchpeer-review

View graph of relations

Continual learning, i.e. the ability to sequentially learn tasks without catastrophic
forgetting of previously learned ones, is an important open challenge in machine
learning. In this paper we take a step in this direction by showing that the recently
proposed Evolving Neural Turing Machine (ENTM) approach is able to perform
one-shot learning in a reinforcement learning task without catastrophic forgetting
of previously stored associations.
Original languageEnglish
Publication date2016
Number of pages5
Publication statusPublished - 2016

Bibliographical note

Best paper award


No data available

ID: 81961425