Related Experiment Video
Updated: May 20, 2026
07:34
A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
Published on: March 25, 2014
Span: spike pattern association neuron for learning spatio-temporal spike patterns.
Ammar Mohemmed1, Stefan Schliebs, Satoshi Matsuda
1Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, New Zealand. amohemme@aut.ac.nz
International Journal of Neural Systems
|July 27, 2012
Summary
This study introduces SPAN, a novel supervised learning algorithm for Spiking Neural Networks (SNNs). SPAN efficiently processes spatio-temporal data by converting spike trains into analog signals for learning synaptic weights.
Area of Science:
- Computational Neuroscience
- Artificial Intelligence
- Machine Learning
Background:
- Spiking Neural Networks (SNNs) excel at processing spatio-temporal information.
- Developing efficient supervised learning algorithms for SNNs is challenging due to their complexity.
Purpose of the Study:
- Introduce SPAN, a novel spiking neuron model for supervised learning.
- Enable SNNs to learn associations of arbitrary spike trains based on precise spike timing.
Main Methods:
- Transforming spike trains into analog signals during the learning phase.
- Applying the Widrow-Hoff rule to adjusted synaptic weights for desired neuron behavior.
Main Results:
- SPAN demonstrates effective learning capabilities and memory capacity.
- The algorithm shows robustness to noisy stimuli and strong classification performance.
Conclusions:
- SPAN offers an efficient supervised learning approach for SNNs.
- The method facilitates processing of precise spike-timing-encoded spatio-temporal information.
