Paper Info
Title
Constructing robust liquid state machines to process highly variable data streams
Abstract
In this paper, we propose a mechanism to effectively control the overall neural activity in the reservoir of a Liquid State Machine (LSM) in order to achieve both a high sensitivity of the reservoir to weak stimuli as well as an improved resistance to over-stimulation for strong inputs. The idea is to employ a mechanism that dynamically changes the firing threshold of a neuron in dependence of its spike activity. We experimentally demonstrate that reservoirs employing this neural model significantly increase their separation capabilities. We also investigate the role of dynamic and static synapses in this context. The obtained results may be very valuable for LSM based real-world application in which the input signal is often highly variable causing problems of either too little or too much network activity.
Year
DOI
Venue
2012
10.1007/978-3-642-33269-2_76
ICANN (1)
Keywords
Field
DocType
liquid state machine,spike activity,robust liquid state machine,network activity,input signal,firing threshold,dynamically change,high sensitivity,variable data stream,overall neural activity,neural model,improved resistance,biology,spiking neural networks,reservoir computing
Data stream mining,Synapse,Pattern recognition,Computer science,Finite-state machine,Liquid state machine,Reservoir computing,Artificial intelligence,Stimulus (physiology),Spiking neural network,Network activity,Machine learning
Conference
Citations 
PageRank 
References 
11
0.64
7
Authors
3
Name
Order
Citations
PageRank
Stefan Schliebs138018.56
Maurizio Fiasché2499.23
Nikola K Kasabov33645290.73