Abstract
The human brain can perform a range of complicated computations and logical reasoning using neural networks with a huge number of neurons. Since Hodgkin and Huxley proposed a set of equations to describe the electro- physiological properties of spiking neurons, various network structures of neurons have been developed through neuroscience research that can now be simulated by electronic circuits or computer programs. In this paper, an adaptive learning mechanism is simulated based on the biological property related to the spike time dependent plasticity of synapses. A demonstration shows that such spiking neurons are able to develop their specific receptive field for recognition of patterns. This mechanism can be used to explain some adaptive behaviours in biological systems. It is can also be applied to artificial intelligent systems.
Original language | English |
---|---|
Title of host publication | Unknown Host Publication |
Publisher | IEEE |
Pages | 1974-1978 |
Number of pages | 5 |
ISBN (Print) | 978-1-4244-0973-0 |
DOIs | |
Publication status | Published (in print/issue) - 1 Aug 2007 |
Event | The International Conference on Machine Learning and Cybernetics (ICMLC2007) - Duration: 1 Aug 2007 → … |
Conference
Conference | The International Conference on Machine Learning and Cybernetics (ICMLC2007) |
---|---|
Period | 1/08/07 → … |
Bibliographical note
Reference text: [1] Yael Adini, Dov Sagi, and Misha Tsodyks, “Context-enabled learning in the human visual system”, Nature, Vol 415, pp.790 – 793, 07 Feb 2002.[2] Michael P. Nusbaum, and Mark P. Beenhakker, “A small-system approach to motor pattern generation”, Nature, 417, pp.343 - 350 , 16 May 2002.
[3] Fre´de´ ric Pouille, Massimo Scanziani, “Routing of spike series by dynamic circuits in the hippocampus”, Nature, Vol 429, pp.717 – 723, 30 May 2004.
[4] L. F. Abbott, and Wade G. Regehr, “Synaptic computation”, Nature, Vol 431, pp.796 – 803, 13 Oct 2004.
[5] Alison Abbott, Neuroscience Deep in thought, Nature, Vol 436, pp.18 – 19, 06 Jul 2005.
[6] E. Müller, “Simulation of High-Conductance States in Cortical Neural Networks”, Masters thesis, University of Heidelberg, HD-KIP-03-22, 2003.
[7] A. Destexhe, E. Marder, “Plasticity in single neuron and circuit computations”, Nature, Vol 431,pp.789 – 795, 2004.
[8] Q. X. Wu, T. M. McGinnity, L. P. Maguire, B. Glackin and A. Belatreche, “Learning Mechanism in Networks of spiking Neurons”, Studies in Computational Intelligence, Springer- Verlag, Vol 35, pp.171–197, 2006.
[9] Q. X. Wu, T. M. McGinnity, L. P. Maguire, A. Belatreche and B. Glackin, “Adaptive Co-Ordinate Transformation Based on Spike Timing-Dependent Plasticity Learning Paradigm”, LNCS, Springer, Vol 3610, pp.420-429, 2005.
[10] SenseMaker Project (IST–2001-34712) funded by the European Union under the “Information Society Technologies” Programme, 2002-2006.
[11] S. Song, and L.F. Abbott, “Column and Map Development and Cortical Re-Mapping Through Spike-Timing Dependent Plasticity”, Neuron, vol 32, pp.339-350, 2001.
[12] Joseph E. Atkins, Robert A. Jacobs, and David C. Knill, “Experience-dependent visual cue recalibration based on discrepancies between visual and haptic percepts”, Vision Research, Vol 43, No. 25, pp.2603-2613, 2003.
Keywords
- Spiking neural network
- computational model
- adaptive learning
- spiking time dependent plasticity