DocumentCode :
62733
Title :
Delay-Based Reservoir Computing: Noise Effects in a Combined Analog and Digital Implementation
Author :
Soriano, M.C. ; Ortin, S. ; Keuninckx, L. ; Appeltant, L. ; Danckaert, J. ; Pesquera, L. ; van der Sande, G.
Author_Institution :
Inst. de Fis. Interdisciplinar y Sist. Complejos, IFISC, Palma de Mallorca, Spain
Volume :
26
Issue :
2
fYear :
2015
fDate :
Feb. 2015
Firstpage :
388
Lastpage :
393
Abstract :
Reservoir computing is a paradigm in machine learning whose processing capabilities rely on the dynamical behavior of recurrent neural networks. We present a mixed analog and digital implementation of this concept with a nonlinear analog electronic circuit as a main computational unit. In our approach, the reservoir network can be replaced by a single nonlinear element with delay via time-multiplexing. We analyze the influence of noise on the performance of the system for two benchmark tasks: 1) a classification problem and 2) a chaotic time-series prediction task. Special attention is given to the role of quantization noise, which is studied by varying the resolution in the conversion interface between the analog and digital worlds.
Keywords :
analogue-digital conversion; chaos; digital-analogue conversion; learning (artificial intelligence); multiplexing; recurrent neural nets; signal classification; time series; ADC; DAC; analog-to-digital converter; chaotic time-series prediction task; classification problem; delay-based reservoir computing; digital-to-analog converter; machine learning; noise effect; nonlinear analog electronic circuit; recurrent neural networks; time-multiplexing; Delays; Hardware; Learning systems; Noise; Numerical simulation; Quantization (signal); Reservoirs; Delay systems; dynamical systems; electronic circuits; memory capacity; pattern recognition; reservoir computing (RC); time-series prediction; time-series prediction.;
fLanguage :
English
Journal_Title :
Neural Networks and Learning Systems, IEEE Transactions on
Publisher :
ieee
ISSN :
2162-237X
Type :
jour
DOI :
10.1109/TNNLS.2014.2311855
Filename :
6782741
Link To Document :
بازگشت