Name
Title | ||
|---|---|---|
Supervised spike-timing-dependent plasticity: A spatiotemporal neuronal learning rule for function approximation and decisions |
Abstract | ||
|---|---|---|
How can an animal learn from experience? How can it train sensors, such as the auditory or tactile system, based on other sensory input such as the visual system? Supervised spike-timing-dependent plasticity supervised STDP is a possible answer. Supervised STDP trains one modality using input from another one as "supervisor." Quite complex time-dependent relationships between the senses can be learned. Here we prove that under very general conditions, supervised STDP converges to a stable configuration of synaptic weights leading to a reconstruction of primary sensory input. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1162/NECO_a_00520 | Neural Computation |
Keywords | Field | DocType |
Supervised STDP,primary sensory input,sensory input,supervised STDP converges,Supervised spike-timing-dependent plasticity,tactile system,visual system,complex time-dependent relationship,general condition,possible answer,function approximation,spatiotemporal neuronal | Supervisor,Function approximation,Computer science,Learning rule,Artificial intelligence,Spike-timing-dependent plasticity,Sensory system,Machine learning | Journal |
Volume | Issue | ISSN |
25 | 12 | 0899-7667 |
Citations | PageRank | References |
0 | 0.34 | 8 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jan-moritz P. Franosch | 1 | 5 | 1.80 |
| Sebastian Urban | 2 | 22 | 5.38 |
| J. Leo van Hemmen | 3 | 819 | 196.53 |