Nik Kasabov, Auckland University of Technology, New Zealand Title: To spike or not to spike? Towards integrative spking neural models

Abstract: To spike, or not to spike? This is the “question” that every neuron in the brain has to “answer” on the millisecond time scale. And the collective “answer” of all neurons at a time makes us learn, act, enjoy life, create art, i.e makes us tic. Many factors define in a concert if a neuron will spike or not at a time, that include input signals, gene and protein expression levels, quantum properties of the nervous system. It has also been demonstrated that neuronal processes are stochastic by nature. Can we integrate these factors and build new types of integrative probabilistic spiking neuronal models? Can we then build a larger scale neural networks? Would that help modeling brain dynamics and solving more efficiently complex engineering problems? A new direction towards building integrative probabilistic spiking neural networks (ipSNN) is presented and illustrated. A quantum inspired probability distribution estimation algorithm is applied to model the activity of many such neurons in order to define optimal states in a parallel fashion. The talk presents a list of challenging problems for future research in the area of ipSNN for classification, time-series prediction, associative memory, string data recognition and others.

References
[1] N.Kasabov (2007) Evolving Connectionist Systems: The Knowledge Engineering Approach, Springer, London
[2] Benuskova and N.Kasabov (2007) Computational Neurogenetic Modelling, Springer, New York
[3] N.Kasabov, Evolving Intelligence in Humans and Machines: Integrative Evolving Connectionist Systems Approach, IEEE Computational Intelligence Magazine, August, 2008, vol.3, N. 3, 23-37
[4] N.Kasabov, Integrative Connectionist Learning Systems Inspired by Nature: Current Models, Future Trends and Challenges, Natural Computing, Springer, 2008
[5] N.Kasabov, Brain-, Gene-, and Quantum Inspired Computational Intelligence: Challenges and Opportunities, in: W. Duch and J. Manzduk (eds) Challenges in Computational Intelligence, Springer, 2007, 193-219
[6] N. Kasabov, Integrative Probabilistic Spiking Neural Networks Utilising Quantum Computation for Probability Evaluation, Proc. ICONIP 2008, Springer, LNCS, vol.5506, 2009

Bio Sketch: Professor Nikola Kasabov is the Founding Director and the Chief Scientist of the Knowledge Engineering and Discovery Research Institute (KEDRI), Auckland (www.kedri.info). He holds a Chair of Knowledge Engineering at the School of Computing and Mathematical Sciences at Auckland University of Technology. He is a Fellow of the Royal Society of New Zealand, Fellow of the New Zealand Computer Society and a Senior Member of IEEE. He is the President of the International Neural Network Society (INNS) for 2009 and 2010. He is a member of several technical committees of the IEEE Computational Intelligence Society and of the IFIP AI TC12. Kasabov is Associate Editor of several international journals, that include Neural Networks, IEEE TrNN, IEEE TrFS, Information Science, J. Theoretical and Computational Nanosciences. He chairs a series of int. conferences ANNES/NCEI in New Zealand. Kasabov holds MSc and PhD from the Technical University of Sofia. His main research interests are in the areas of intelligent information systems, soft computing, neuro-computing, bioinformatics, brain study, speech and image processing, novel methods for data mining and knowledge discovery. He has published more than 400 publications that include 15 books, 120 journal papers, 60 book chapters, 32 patents and numerous conference papers. He has extensive academic experience at various academic and research organisations: University of Otago, New Zealand; University of Essex, UK; University of Trento, Italy; Technical University of Sofia, Bulgaria; University of California at Berkeley; RIKEN and KIT, Japan; TUniversity Kaiserslautern, Germany, and others. More information of Prof. Kasabov can be found on the KEDRI web site: http://www.kedri.info.