Počet záznamů: 1
On the Complexity of Training a Single Perceptron with Programmable Synaptic Delays
- 1.0404917 - UIVT-O 20030045 RIV DE eng C - Konferenční příspěvek (zahraniční konf.)
Šíma, Jiří
On the Complexity of Training a Single Perceptron with Programmable Synaptic Delays.
Algorithmic Learning Theory. Berlin: Springer, 2003 - (Gavalda, R.; Jantke, K.; Takimoto, E.), s. 221-233. Lecture Notes in Artificial Intelligence, 2842. ISBN 3-540-20291-9. ISSN 0302-9743.
[ALT'2003. International Conference on Algorithmic Learning Theory /14./. Sapporo (JP), 17.10.2003-19.10.2003]
Grant CEP: GA MŠMT LN00A056
Klíčová slova: spiking neuron * synaptic delays * loading problem * PAC learning * robust learning
Kód oboru RIV: BA - Obecná matematika
We consider a single perceptron N with synaptic delays which generalizes a simplified model for a spiking neuron where not only the time that a pulse needs to travel through a synapse is taken into account but also the input firing rates may have more different levels. A synchronization technique is introduced so that the results concerning the learnability of spiking neurons with binary delays also apply to N with arbitrary delays. In particular, the consistency problem for N with programmable delays and..
Trvalý link: http://hdl.handle.net/11104/0125138
Název souboru Staženo Velikost Komentář Verze Přístup 0404917.pdf 0 387.9 KB Autorský preprint povolen
Počet záznamů: 1