Artificial Neural Network Model Adopting Combinatorial Inhibition Process in Multiple Solution Problems

  • Authors

    • K Shyamala
    • P Chanthini
    • R Krishnan
    • A Murugan
    2018-06-25
    https://doi.org/10.14419/ijet.v7i3.4.16767
  • Combinatorics, Inhibition, Non-Modular neural network, Selection, Sequential Firing

  • Abstract

    Exploration of Artificial Neural Network (ANN) research continually opens rooms for improvement and implementation of mathematical models to solve various problems. This research work was not only to direct on the objective of problem-solving, instead the goal is to mimic basic biological functions of the brain in problem-solving situations. The basic biological theories of “Selectionâ€, “Combination†and “Inhibition†were successfully implemented in the earlier works. This work conceived another biological theory named “Sequential Firing†of neuron in solving complex problems like sum-of-subset problems. The non-modular combinatorial inhibition neural model has been proposed and implemented successfully using the time delayed sequential firing between neurons. As per the biological theories knowledge representation is a preliminary phase of learning. This work not only illustrates the sequential process of firing between neurons, it paves the way to utilize this neural model for the learning process.

     

  • References

    1. [1] Chanthini P, Shyamala K, “Neural Darwinism Inspired Implementation of an Artificial Neural Network Model,†International Journal of Control Theory and Applications. Vol 10 (23), pp 7-16, 2017.

      [2] Edelman, Gerald M. “Neural Darwinism: Selection and reentrant signaling in higher brain function,†Neuron, vol. 10(2), pp. 115-125, Feb. 1993.

      [3] Shyamala, K., Chanthini, P.: A Novel Approach in Solving 0/1 Knapsack Problem Using Neural Selection Principle. IEEE International Conference on Power, Control, Signals and Instrumentation Engineering. Issue-III., pp. 305--309 (2017).

      [4] Shyamala K, Chanthini P, “Sum-of-Subset Implementation Using Neural Selection Principle and Cognitive Process of Inhibition,†has been “Accepted†in 1st International Conference on Communication, Networks & Computing (CNC – 2018), ITM University Gwalior, 22nd – 24th March 2018, Springer CCIS (“in-pressâ€).

      [5] Wang, Xiao-Jing. "Decision making in recurrent neuronal circuits." Neuron 60.2 (2008): 215-234.

      [6] Shenoy, Pradeep, and Angela J. Yu. "Rational decision-making in inhibitory control." Frontiers in human neuroscience5 (2011): 48.

      [7] Elizondo, D., and Emile Fiesler. "A survey of partially connected neural networks." International journal of neural systems 8.05n06 (1997): 535-558.

      [8] LeCun, Yann, John S. Denker, and Sara A. Solla. "Optimal brain damage." Advances in neural information processing systems. 1990.

      [9] Sanger, Terence D. "Optimal unsupervised learning in a single-layer linear feedforward neural network." Neural networks 2.6 (1989): 459-473.

      [10] Kung, S. Y., J. N. Hwang, and S. W. Sun. "Efficient modeling for multilayer feed-forward neural nets." Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on. IEEE, 1988.

      [11] Provence, John D., and S. Naganathan. "Locally versus globally interlayer-connected feed-forward neural networks: a performance comparison." Applications of Artificial Intelligence VIII. Vol. 1293. International Society for Optics and Photonics, 1990.

      [12] Redding, N. J., A. Kowalczyk, and T. Downs. "Higher order separability and minimal hidden-unit fan-in." Artificial neural networks 1 (1991): 25-30.

      [13] El-Shafie, Ahmed, et al. "Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia." Hydrology and Earth System Sciences 16.4 (2012): 1151-1169.

      [14] Lu, Wenlian, and Tianping Chen. "Synchronization of coupled connected neural networks with delays." IEEE Transactions on Circuits and Systems I: Regular Papers 51.12 (2004): 2491-2503.

      [15] Kang, Min-Suk, and Joongrul Choi. "Retrieval-induced inhibition in short-term memory." Psychological science 26.7 (2015): 1014-1025.

      [16] Tepper, James M., Charles J. Wilson, and Tibor Koós. "Feedforward and feedback inhibition in neostriatal GABAergic spiny neurons." Brain research reviews 58.2 (2008): 272-281.

      Shyamala, K., Chanthini,P., Krishnan,R., and A. Murugan. “Adoption of combinatorial graph for inhibitory process in optimization problems.†International Journal of Applied Engineering Research (IJAER) (2018)(“in-pressâ€).

  • Downloads

  • How to Cite

    Shyamala, K., Chanthini, P., Krishnan, R., & Murugan, A. (2018). Artificial Neural Network Model Adopting Combinatorial Inhibition Process in Multiple Solution Problems. International Journal of Engineering & Technology, 7(3.4), 167-173. https://doi.org/10.14419/ijet.v7i3.4.16767

    Received date: 2018-08-03

    Accepted date: 2018-08-03

    Published date: 2018-06-25