Temporal Hebbian Learning in Rate-Coded Neural Networks: A Theoretical Approach towards Classical Conditioning
2001 | conference paper
Jump to: Cite & Linked | Documents & Media | Details | Version history
Cite this publication
Temporal Hebbian Learning in Rate-Coded Neural Networks: A Theoretical Approach towards Classical Conditioning
Porr, B. & Woergoetter, F. (2001)
In:Dorffner, Georg; Bischof, Horst; Hornik, Kurt (Eds.), Artificial Neural Networks — ICANN 2001 pp. 1115-1120. ICANN: International Conference on Artificial Neural Networks, Vienna.
Berlin, Heidelberg: Springer. DOI: https://doi.org/10.1007/3-540-44668-0_155
Documents & Media
Details
- Authors
- Porr, Bernd; Woergoetter, Florentin
- Editors
- Dorffner, Georg; Bischof, Horst; Hornik, Kurt
- Abstract
- A novel approach for learning of temporally extended, continuous signals is developed within the framework of rate coded neurons. A new temporal Hebb like learning rule is devised which utilizes the predictive capabilities of bandpass filtered signals by using the derivative of the output to modify the weights. The initial development of the weights is calculated analytically applying signal theory and simulation results are shown to demonstrate the performance of this approach. In addition we show that only few units suffice to process multiple inputs with long temporal delays.
- Issue Date
- 2001
- Publisher
- Springer
- Conference
- ICANN: International Conference on Artificial Neural Networks
- Series
- Lecture Notes in Computer Science
- ISBN
- 978-3-540-42486-4
- Conference Place
- Vienna
- Event start
- 2001-08-21
- Event end
- 2001-08-25
- ISSN
- 0302-9743
- Language
- English