Published 1996
| Published
Book Section - Chapter
Open
Universal Approximation and Learning of Trajectories Using Oscillators
- Creators
- Baldi, Pierre
- Hornik, Kurt
Abstract
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.
Additional Information
© 1996 Massachusetts Institute of Technology. The work of PB is in part supported by grants from the ONR and the AFOSR.Attached Files
Published - 1062-universal-approximation-and-learning-of-trajectories-using-oscillators.pdf
Files
1062-universal-approximation-and-learning-of-trajectories-using-oscillators.pdf
Files
(1.6 MB)
Name | Size | Download all |
---|---|---|
md5:a8307c4d3d7dbd712c5e4535d0cea96a
|
1.6 MB | Preview Download |
Additional details
- Eprint ID
- 64677
- Resolver ID
- CaltechAUTHORS:20160223-113949077
- Office of Naval Research (ONR)
- Air Force Office of Scientific Research (AFOSR)
- Created
-
2016-02-23Created from EPrint's datestamp field
- Updated
-
2019-10-03Created from EPrint's last_modified field
- Series Name
- Advances in Neural Information Processing Systems
- Series Volume or Issue Number
- 8