A Caltech Library Service

Universal Approximation and Learning of Trajectories Using Oscillators

Baldi, Pierre and Hornik, Kurt (1996) Universal Approximation and Learning of Trajectories Using Oscillators. In: Advances in Neural Information Processing Systems 8 (NIPS 1995). Advances in Neural Information Processing Systems. No.8. MIT Press , Cambridge, MA, pp. 451-457. ISBN 0-262-20107-0.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Natural and artificial neural circuits must be capable of traversing specific state space trajectories. A natural approach to this problem is to learn the relevant trajectories from examples. Unfortunately, gradient descent learning of complex trajectories in amorphous networks is unsuccessful. We suggest a possible approach where trajectories are realized by combining simple oscillators, in various modular ways. We contrast two regimes of fast and slow oscillations. In all cases, we show that banks of oscillators with bounded frequencies have universal approximation properties. Open questions are also discussed briefly.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Additional Information:© 1996 Massachusetts Institute of Technology. The work of PB is in part supported by grants from the ONR and the AFOSR.
Funding AgencyGrant Number
Office of Naval Research (ONR)UNSPECIFIED
Air Force Office of Scientific Research (AFOSR)UNSPECIFIED
Series Name:Advances in Neural Information Processing Systems
Issue or Number:8
Record Number:CaltechAUTHORS:20160223-113949077
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:64677
Deposited On:23 Feb 2016 19:47
Last Modified:03 Oct 2019 09:40

Repository Staff Only: item control page