Title :
Sequence learning and generation using a spiking neural network
Author :
Watanabe, Fuyuko ; Fujii, Robert H.
Author_Institution :
Comput. Syst. Dept., Univ. of Aizu, Aizu-Wakamatsu, Japan
Abstract :
A new neural network that uses the ReSuMe supervised learning algorithm for generating a desired spike output sequence in response to a given input spike sequence is proposed. Possible advantages of the proposed new neural network system compared to the Liquid State Machine based ReSuMe network system include better learning convergence and a smaller neural network size.
Keywords :
learning (artificial intelligence); neural nets; ReSuMe network system; ReSuMe supervised learning algorithm; input spike sequence; learning convergence; liquid state machine; neural network size; sequence generation; sequence learning; spike output sequence; spiking neural network; Biological neural networks; Convergence; Education; Equations; Firing; Mathematical model; Neurons; Liquid State Machine; sequence generation; sequence learning; spiking neuron;
Conference_Titel :
Communications and Electronics (ICCE), 2012 Fourth International Conference on
Conference_Location :
Hue
Print_ISBN :
978-1-4673-2492-2
DOI :
10.1109/CCE.2012.6315957
