Dynamical learning of dynamics release_mqfkp3g5vnfiphpqt4xnvgctra

by Christian Klos, Yaroslav Felipe Kalle Kossio, Sven Goedeke, Aditya Gilra, Raoul-Martin Memmesheimer

Released as a article .

2020  

Abstract

The ability of humans and animals to quickly adapt to novel tasks is difficult to reconcile with the standard paradigm of learning by slow synaptic weight modification. Here we show that fixed-weight neural networks can learn to generate required dynamics by imitation. After appropriate weight pretraining, the networks quickly and dynamically adapt to learn new tasks and thereafter continue to achieve them without further teacher feedback. We explain this ability and illustrate it with a variety of target dynamics, ranging from oscillatory trajectories to driven and chaotic dynamical systems.
In text/plain format

Archived Content

There are no accessible files associated with this release. You could check other releases for this work for an accessible version.

"Dark" Preservation Only
Save Paper Now!

Know of a fulltext copy of on the public web? Submit a URL and we will archive it

Type  article
Stage   accepted
Date   2020-08-25
Version   v3
Language   en ?
arXiv  1902.02875v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: aad422bf-e2b6-4700-a5eb-6e7670be8a2f
API URL: JSON