Validation Testing for Temporal Neural Networks for RBF Recognition
A neuron can emit spikes in an irregular time basis and by averaging over a certain time window one would ignore a lot of information. It is known that in the context of fast information processing there is no sufficient time to sample an average firing rate of the spiking neurons. The present work shows that the spiking neurons are capable of computing the radial basis functions by storing the relevant information in the neurons' delays. One of the fundamental findings of the this research also is that when using overlapping receptive fields to encode the data patterns it increases the network-s clustering capacity. The clustering algorithm that is discussed here is interesting from computer science and neuroscience point of view as well as from a perspective.
[1] W. Mass, Networks of spiking neurons: the third generation of neural
network models, Neural Networks, 10, 1998. pp.1659-1671.
[2] L. Guo, D-H. Huang, and W. Zhao, Combining Genetic Optimization
with Hybrid Learning Algorithm for Radial Basis Function Neural
Networks, Neural Networks, 2003. Proc. of the International Joint
Conference on Neural Networks Vol. 4, 2003, pp.3213 - 3217.
[3] T. S Sejnowski, Time for a new neural code?, Nature, 376, 1995, pp.
21-22., A
[4] M. Abeles, M., A., Corticonics, Neural Circuits of the Cerebral
Cortex, Cambridge University Press, 1991.,
[5] M. Abeles, H. Bergman, H., Margalit, and E. Vaadia, Spationtemporal
firing patterns in the frontal cortex of behaving monkeys, Journal of
Neurophysiology, 70, 1993, pp. 1629-1638.
[6] Z. Mainen, and T. Sejnowski, Reliability of spike timing in
neocortical neurons, Science, 268, 1995, pp.1503-1506.
[7] R. Rieke, F. Warland, D., Bialek, and R. Van Steveninck., SPIKES:
Exploring the Neural Code, MIT-Press, Cambridge, 1996.
[8] S. Thorpe, S. Fize, and C. Marlot, Speed of processing in the human
visual system, Nature, 381, 1996, pp. 520-522.
[9] S. Thorpe and M. Imbert, Biological constraints on connectionist
modeling. In Pfeifer, R., Schreter, Z., Fogelman-Soulie, F., and Steels,
L., editors, Connectionism in Perspective. Elsevier Publisher, 1989.
[10] W. Mass, Lower bounds for the computational power of networks of
spiking neurons. Neural Computation, 8, 1996, pp. 1-40, 1996.
[11] W. Mass, Fast sigmoidal networks via spiking neurons, Neural
Computation, 9, 1997, pp. 279-304.
[12] C. Allipi, V. Piuri, and F. Scotti, Accuracy versus Comlixty in RBF
Neural Networks, IEEE Instrumentation and Measurement, 4, 2001,
pp. 32-36.
[13] T. Gawne, T. Kjaer. and M. Richmond, Latency: Another potential
code for feature binding in striate cortex, J. of Neurophysiology, 76,
1996, pp. 1356-1360.
[14] J. O-Keefe and M.Reece, Phase relationship between hippocampal
place units and the EEG theta rhythm. Hippocampus, 3, 1993, pp.
317-330.
[15] S. Thorpe and M. Imbert., Rapid visual processing using spike
synchrony. In Advances in neural processing systems, 9, 1996, pp.
901-907, MIT Press, Cambridge.
[16] J. Moody, and C. Darken, Fast learning in networks of locally-tuned
processing units, Neural Comp, 1, 1989, pp. 281-294.
[17] D. Broomhead, and D. Lowe, Multivariable functional interpolation
and adaptive networks, Complex Systems, 2, 1988, pp. 321-355.
[18] S. Haykin, Neural Networks: a comprehensive foundation, Prentice
Hall, 1994.
[19] C. Bishop, Neural Networks for Pattern Recognition, Clarendon
Press, Oxford, 1995.
[20] J. Hopfield, Pattern recognition computation using action potential
timing for stimulus representation, Nature, 376, 1995, pp. 33-36.
[21] S. Buck, RBF++, Munich University of Technology, Software
Library, Ver. 1.2, 2002.
[22] T. Natschlager, T. and R. Ruf., Spatial and temporal pattern analysis
via spiking neurons Network, Computation in Neural Systems, 9,
1998, pp. 319-332.
[23] K. Negm, Real Time UNIX Kernel Based Intrusion Detection System,
Proc. of International Conference of Intelligent Systems and Control.
2002, pp 126-138.
[24] K. Negm, Double Step Intrusion Detection System, Proc. of
International Conference of Intelligent Systems and Control, 2003, pp
26-32.
[1] W. Mass, Networks of spiking neurons: the third generation of neural
network models, Neural Networks, 10, 1998. pp.1659-1671.
[2] L. Guo, D-H. Huang, and W. Zhao, Combining Genetic Optimization
with Hybrid Learning Algorithm for Radial Basis Function Neural
Networks, Neural Networks, 2003. Proc. of the International Joint
Conference on Neural Networks Vol. 4, 2003, pp.3213 - 3217.
[3] T. S Sejnowski, Time for a new neural code?, Nature, 376, 1995, pp.
21-22., A
[4] M. Abeles, M., A., Corticonics, Neural Circuits of the Cerebral
Cortex, Cambridge University Press, 1991.,
[5] M. Abeles, H. Bergman, H., Margalit, and E. Vaadia, Spationtemporal
firing patterns in the frontal cortex of behaving monkeys, Journal of
Neurophysiology, 70, 1993, pp. 1629-1638.
[6] Z. Mainen, and T. Sejnowski, Reliability of spike timing in
neocortical neurons, Science, 268, 1995, pp.1503-1506.
[7] R. Rieke, F. Warland, D., Bialek, and R. Van Steveninck., SPIKES:
Exploring the Neural Code, MIT-Press, Cambridge, 1996.
[8] S. Thorpe, S. Fize, and C. Marlot, Speed of processing in the human
visual system, Nature, 381, 1996, pp. 520-522.
[9] S. Thorpe and M. Imbert, Biological constraints on connectionist
modeling. In Pfeifer, R., Schreter, Z., Fogelman-Soulie, F., and Steels,
L., editors, Connectionism in Perspective. Elsevier Publisher, 1989.
[10] W. Mass, Lower bounds for the computational power of networks of
spiking neurons. Neural Computation, 8, 1996, pp. 1-40, 1996.
[11] W. Mass, Fast sigmoidal networks via spiking neurons, Neural
Computation, 9, 1997, pp. 279-304.
[12] C. Allipi, V. Piuri, and F. Scotti, Accuracy versus Comlixty in RBF
Neural Networks, IEEE Instrumentation and Measurement, 4, 2001,
pp. 32-36.
[13] T. Gawne, T. Kjaer. and M. Richmond, Latency: Another potential
code for feature binding in striate cortex, J. of Neurophysiology, 76,
1996, pp. 1356-1360.
[14] J. O-Keefe and M.Reece, Phase relationship between hippocampal
place units and the EEG theta rhythm. Hippocampus, 3, 1993, pp.
317-330.
[15] S. Thorpe and M. Imbert., Rapid visual processing using spike
synchrony. In Advances in neural processing systems, 9, 1996, pp.
901-907, MIT Press, Cambridge.
[16] J. Moody, and C. Darken, Fast learning in networks of locally-tuned
processing units, Neural Comp, 1, 1989, pp. 281-294.
[17] D. Broomhead, and D. Lowe, Multivariable functional interpolation
and adaptive networks, Complex Systems, 2, 1988, pp. 321-355.
[18] S. Haykin, Neural Networks: a comprehensive foundation, Prentice
Hall, 1994.
[19] C. Bishop, Neural Networks for Pattern Recognition, Clarendon
Press, Oxford, 1995.
[20] J. Hopfield, Pattern recognition computation using action potential
timing for stimulus representation, Nature, 376, 1995, pp. 33-36.
[21] S. Buck, RBF++, Munich University of Technology, Software
Library, Ver. 1.2, 2002.
[22] T. Natschlager, T. and R. Ruf., Spatial and temporal pattern analysis
via spiking neurons Network, Computation in Neural Systems, 9,
1998, pp. 319-332.
[23] K. Negm, Real Time UNIX Kernel Based Intrusion Detection System,
Proc. of International Conference of Intelligent Systems and Control.
2002, pp 126-138.
[24] K. Negm, Double Step Intrusion Detection System, Proc. of
International Conference of Intelligent Systems and Control, 2003, pp
26-32.
@article{"International Journal of Information, Control and Computer Sciences:54755", author = "Khaled E. A. Negm", title = "Validation Testing for Temporal Neural Networks for RBF Recognition", abstract = "A neuron can emit spikes in an irregular time basis and by averaging over a certain time window one would ignore a lot of information. It is known that in the context of fast information processing there is no sufficient time to sample an average firing rate of the spiking neurons. The present work shows that the spiking neurons are capable of computing the radial basis functions by storing the relevant information in the neurons' delays. One of the fundamental findings of the this research also is that when using overlapping receptive fields to encode the data patterns it increases the network-s clustering capacity. The clustering algorithm that is discussed here is interesting from computer science and neuroscience point of view as well as from a perspective.
", keywords = "Temporal Neurons, RBF Recognition, Perturbation, On Line Recognition.", volume = "1", number = "5", pages = "1267-6", }
