Abstract | ||
---|---|---|
Echo State Newtworks (ESNs) are simplified recurrent neural network models composed of a reservoir and a linear, trainable readout layer. The reservoir is tunable by some hyper-parameters that control the network behaviour. ESNs are known to be effective in solving tasks when configured on a region in (hyper-)parameter space called Edge of Criticality (EoC), where the system is maximally sensitive to perturbations hence affecting its behaviour. In this paper, we propose binary ESNs, which are architecturally equivalent to standard ESNs but consider binary activation functions and binary recurrent weights. For these networks, we derive a closed-form expression for the EoC in the autonomous case and perform simulations in order to assess their behavior in the case of noisy neurons and in the presence of a signal. We propose a theoretical explanation for the fact that the variance of the input plays a major role in characterizing the EoC. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/MLSP.2018.8516959 | 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP) |
Keywords | DocType | Volume |
Reservoir computing,Binarization,Random Boolean networks,Edge of Criticality | Conference | abs/1810.01742 |
ISSN | ISBN | Citations |
1551-2541 | 978-1-5386-5478-1 | 0 |
PageRank | References | Authors |
0.34 | 5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pietro Verzelli | 1 | 1 | 1.71 |
Lorenzo Livi | 2 | 304 | 25.67 |
Cesare Alippi | 3 | 1040 | 115.84 |