Progress & Compress: A scalable framework for continual learning

We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-07
Main Authors: Schwarz, Jonathan, Luketina, Jelena, Czarnecki, Wojciech M, Grabska-Barwinska, Agnieszka, Teh, Yee Whye, Pascanu, Razvan, Hadsell, Raia
Format: Article
Language:English
Subjects:
Domains
Handwriting
Knowledge base
Maze learning
Parameters
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is achieved by training a network with two components: A knowledge base, capable of solving previously encountered problems, which is connected to an active column that is employed to efficiently learn the current task. After learning a new task, the active column is distilled into the knowledge base, taking care to protect any previously acquired skills. This cycle of active learning (progression) followed by consolidation (compression) requires no architecture growth, no access to or storing of previous data or tasks, and no task-specific parameters. We demonstrate the progress & compress approach on sequential classification of handwritten alphabets as well as two reinforcement learning domains: Atari games and 3D maze navigation.
ISSN:2331-8422