Learning, Inference, and Replay of Hidden State Sequences in Recurrent Spiking Neural Networks

Learning to recognize, predict, and generate spatio-temporal patterns and sequences of spikes is a key feature of nervous systems, and essential for solving basic tasks like localization and navigation. How this can be done by a spiking network, however, remains an open question. Here we present a STDP-based framework extending a previous model [1], that can simultaneously learn to abstract hidden states from sensory inputs and learn transition probabilities [2] between these states in recurrent connection weights.


Advisor(s):
Gerstner, Wulfram
Presented at:
COSYNE 2014, Salt Lake City & Snowbird, Utah, USA, February 27 - March 4, 2014
Year:
2014
Laboratories:




 Record created 2014-03-07, last modified 2018-11-26

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)