Conditional plasticity spiking neuron network apparatus and methods

作者: Filip Piekniewski

DOI:

关键词:

摘要: Apparatus and methods for conditional plasticity in a neural network. In one approach, mechanism is configured to select alternate rules when performing connection updates. The selection adapted based on comparison of actual efficiency target efficiency. For instance, below the value, STDP rule may be modulated increase long term potentiation. Similarly, above depression. dynamically adjusts efficacy, prevents uncontrolled weights, thereby improving network operation processing information varying nature.

参考文章(74)
Anthony Ndirango, Bipin Rajendran, Steven K. Esser, Dharmendra S. Modha, Phase change memory synaptronic circuit for spiking computation, association and recall ,(2010)
Jayram Moorkanikara Nageswaran, Filip Lukasz Piekniewski, Csaba Petre, Botond Szatmary, Sach Hansen Sokol, Eugene M. Izhikevich, Apparatus and methods for temporally proximate object recognition ,(2011)
Filip Piekniewski, Csaba Petre, Botond Szatmary, Eugene Izhikevich, Sensory input processing apparatus in a spiking neural network ,(2012)
Brad Smallridge, Arthur Zay Gaffin, Visual imaging system and method ,(1995)
Simon Thorpe, None, Ultra-Rapid Scene Categorization with a Wave of Spikes BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision. pp. 1- 15 ,(2002) , 10.1007/3-540-36181-2_1