Liquid computing and analysis of sound signals

• Autorzy: Cebryk R. , Wójcik G. M.

Identyfikatory

DOI

10.2478/umcsinfo-2014-0023

• Języki publikacji: EN

Abstrakty

EN

Liquid Computing Theory is a proposal of modelling the behaviour of neural microcircuits.It focuses on creating a group of neurons, known as a liquid layer, responsible for preprocessing of the signal that is being analysed. Specific information is achieved by the readout layers, task oriented groups of neurons, taught to extract particular information from the state of liquid layer. The LSMs have been used to analyse sound signals. The liquid layer was implemented in the PCSIM Simulator, and the readout layer has been prepared in the JNNS simulator. It could successfully recognise certain sounds despite noises. Those results encourage further research of the computational potentialof Liquid State Machines including working in parallel with many readout layers.

Słowa kluczowe

EN

Liquid Computing Theory; neural microcircuits; Liquid State Machine; LSM

• Wydawca: Wydawnictwo UMCS
• Czasopismo: Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica
• Rocznik: 2014
• Tom: Vol. 14, no. 3
• Strony: 33--42
• Opis fizyczny: Bibliogr. 15 poz., rys., tab.

Twórcy

autor

Cebryk R.

• Institute of Computer Science, Maria Curie-Sklodowska University, Akademicka 9, 20-033 Lublin, Poland

autor

Wójcik G. M.

• Institute of Computer Science, Maria Curie-Sklodowska University, Akademicka 9, 20-033 Lublin, Poland

Bibliografia

• [1] R. Tadeusiewicz, “Modelowanie elementów systemu nerwowego z wykorzystaniem technik informatycznych, a zwłaszcza sztucznych sieci neuronowych” in “Na ścieżkach neuronauk pod redakcją naukową Piotra Fracuza”, pages 13-34, Wydawnictwo KUL, 2010.
• [2] R. Tadeusiewicz, “Modele elementów układu nerwowego w postaci sztucznych sieci neuronowych” in “Neurocybernetyka Teoretyczna”, pages 109-127, Wydawnictwa Uniwersytetu Warszawskiego, 2009.
• [3] R. Tadeusiewicz, “Using Neural Networks for Simplified Discovery of Some Psychological Phenomena” in “Artificial Intelligence and Soft Computing”, Lecture Notes in Artificial Intelligence, L. Rutkowski et al., eds., editor, pages 104-123, vol. 6114, Springer-Verlag, Berlin – Heidelberg – New York, 2010.
• [4] D. Verstraeten, B. Schrauwen and D. Stroobandt, "Isolated word recognition using a Liquid State Machine" in ESSANN’2005 proceedings - European Symposium on Artificial Neural Networks, Bruges (Belgium).
• [5] W. Maass, T. Natschlaeger, and H. Markram. Computational models for generic cortical microcircuits. In Computational Neuroscience: A Comprehensive Approach, J. Feng, editor, chapter 18, pages 575-605, Boca Raton, 2004.
• [6] W. Maass, “Computation with spiking neurons,” in The Handbook of Brain Theory and Neural Networks (M. A. Arbib, ed.), pp. 1080–1083, 2 ed., 2003.
• [7] W. Maass and H. Markram, “On the computational power of recurrent circuits of spiking neurons,” Journal of Computer and System Sciences, vol. 69, no. 4, pp. 593–616, 2004.
• [8] W. Maass, “Liquid computing,” in Computability in Europe 2007 - CiE’07, Springer (Berlin), 2007.
• [9] “PCSIM: A Parallel neural Circuit SIMulator.” http://www.lsm.tugraz.at/pcsim/.
• [10] “What is SNNS?” http://www.ra.cs.uni-tuebingen.de/SNNS/announce.html.
• [11] “Python Programming Language – Official Website.” http://www.python.org/.
• [12] W. Maass, T. Natschlaeger, and H. Markram, “Real-time Computing without stable states: A New Framework for Neural Computation Based on Perturbations,” Neural Computation, vol. 14, no. 11, pp. 2531–2560, 2002.
• [13] G. M. Wojcik and J. A. Garcia-Lazaro, "Analysis of the neural hypercolumn in parallel pcsim simulations," Procedia Computer Science, vol. 1, no. 1, pp. 845-854, 2010.
• [14] G. M.Wojcik, "Self-organising criticality in the simulated models of the rat cortical microcircuits," Neurocomputing, no. 79, pp. 61-67, 2012.
• [15] G. M. Wojcik, "Electrical parameters influence on the dynamics of the hodgkin-huxley liquid state machine," Neurocomputing, no. 79, pp. 68-78, 2012.