Guessing can Outperform Many Long Time Lag Algorithms

Authors:
Juergen Schmidhuber;Sepp Hochreiter
Affiliations:
-;-
Venue:
Guessing can Outperform Many Long Time Lag Algorithms
Year:
1996

Citing 0
Cited 2

Long Short-Term Memory

Neural Computation
Neuroevolution strategies for episodic reinforcement learning

Journal of Algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

Numerous recent papers focus on standard recurrent nets'' inability to deal with long time lags between relevant signals. Some propose rather sophisticated, alternative methods. We show: many problems used to test previous algorithms can be solved more quickly by random weight guessing.