Levenberg-Marquardt Learning Algorithm for Integrate-and-Fire Neuron Model

In this paper, Levenberg-Marquardt (LM) learning algorithm for a single Integrate-and-Fire Neuron (IFN) is proposed and tested for various applications in which a neural network based on multilayer perceptron is conventionally used. It is found that a single IFN is sufficient for the applications that require a number of neurons in different hidden layers of a conventional neural network. Several benchmark and real-life problems of classification and function-approximation have been illustrated. It is observed that the inclusion of robust algorithm and more biological phenomenon in an artificial neural network can make it more powerful. Keywords—Levenberg-Marquardt learning algorithm, Integrate-and-Fire neuron model, Multilayer Perceptron, Classification, Function approximation.

[1]  T. Poggio,et al.  Multiplying with synapses and neurons , 1992 .

[2]  Jianfeng Feng,et al.  Training integrate-and-fire neurons with the Informax principle II , 2003, IEEE Trans. Neural Networks.

[3]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[4]  S. Kaplan.  The Physiology of Thought , 1950 .

[5]  Jianfeng Feng.  Neuronal Models with Current Inputs , 2001, IWANN.

[6]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[7]  Andrew D. Back,et al.  A spiking neural network architecture for nonlinear function approximation , 2001, Neural Networks.

[8]  Vivien A. Casagrande,et al.  Biophysics of Computation: Information Processing in Single Neurons , 1999 .

[9]  A. Hodgkin,et al.  A quantitative description of membrane current and its application to conduction and excitation in nerve , 1952, The Journal of physiology.

[10]  W. J. Freeman.  Why neural networks don't yet fly: inquiry into the neurodynamics of biological intelligence , 1988, IEEE 1988 International Conference on Neural Networks.

[11]  Prem Kumar Kalra,et al.  Chaotic Behavior in Neural Networks and FitzHugh-Nagumo Neuronal Model , 2004, ICONIP.

[12]  Yogesh Singh,et al.  Feedforward sigmoidal networks - equicontinuity and fault-tolerance properties , 2004, IEEE Transactions on Neural Networks.

[13]  Shih-Chii Liu,et al.  Temporal coding in a silicon network of integrate-and-fire neurons , 2004, IEEE Transactions on Neural Networks.

[14]  S. Ray,et al.  Learning with single integrate-and-fire neuron , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[15]  Jianfeng Feng,et al.  Training the integrate-and-fire model with the informax principle: I , 2002 .

[16]  Bedrich J. Hosticka,et al.  Biologically-inspired artificial neurons: modeling and applications , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[17]  S. Thomas Alexander,et al.  Adaptive Signal Processing , 1986, Texts and Monographs in Computer Science.

[18]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[19]  Prem Kalra,et al.  Classification using single neuron , 2003, IEEE International Conference on Industrial Informatics, 2003. INDIN 2003. Proceedings..