Abstract
Though the Artificial Neural Network is used as a potential tool to solve many of the real-world learning and adaptation problems, the research articles revealing the simple facts of how to simulate an artificial neuron for most popular tasks are very scarce. This paper has in its objective presenting the details of design and implementation of artificial neurons for linearly separable Boolean functions. The simple Boolean functions viz AND and OR are taken for the study. This paper initially presents the simulation details of artificial neurons for AND and OR operations, where the required weight values are manually calculated. Next, the neurons are added with learning capability with perceptron learning algorithm and the iterative adaptation of weight values are also presented in the paper.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mandziuk, J., Macukow, B.: A neural network performing boolean logic operations. Opt. Mem. Neural Netw. 2(1), 17–35 (1993)
Dubois, D.M.: Hyperincursive McCulloch and Pitts neurons for designing a computing flip-flop memory. In: Computing Anticipatory Systems: CASYS 1998 - Second International Conference, pp. 3–21 (1999)
Kohut, R., Steinbach, B.: Boolean neural networks. In: Proceedings Kohut 2004 (2004)
Ele, S.I., Adesola, W.A.: Artificial neuron network implementation of boolean logic gates by perceptron and threshold element as neuron output function. Int. J. Sci. Res. 4(9), 637–641 (2013)
Srinivas Raju, J.S., Kumar, S., Sai Sneha, L.V.S.S.: Realization of logic gates using MccullochPitts neuron model. Int. J. Eng. Trends Technol. 45(2), 52–56 (2017)
Sun, X., Peng, X., Chen, P.-Y., Liu, R., Seo, J., Yu, S.: Fully parallel RRAM synaptic array for implementing binary neural network with (+1, −1) Weights and (+1, 0) neurons. In: 23rd Asia and South Pacific Design Automation Conference (ASP-DAC), pp. 574–579 (2018)
Dong, H.-W., Yang, Y.-H.: Training generative adversarial networks with binary neurons by end-to-end back propagation. Comput. Res. Repository (2018). arXiv:1810.04714
Torres-Moreno, J.-M., Gordon, M.B.: Adaptive learning with binary neurons. arXiv:0904.4587 (2009)
Skubiszewski, M.: A hardware emulator for binary neural networks. In: International Neural Network Conference, Springer, Dordrecht (1990)
Fujii, T., Sato, S., Nakahara, H.: A threshold neuron pruning for a binarized deep neural network on an FPGA. IEICE Trans. Inf. Syst. 101(2), 376–386 (2018)
Kohut, R., Steinbach, B.: The structure of boolean neuron for the optimal mapping to FPGAs. In: Proceedings of the VIII-th International Conference CADSM 2005, pp. 469–473 (2005)
Training with states of matter search algorithm enables neuron model pruning, Technical report - Kanazawa University, November 2018
Bindu, K.R., Aakash, C., Orlando, B., Parameswaran, L.: An algorithm for text prediction using neural networks. In: Lecture Notes in Computational Vision and Biomechanics, vol, 28, pp. 186–192 (2018)
Kumar, P.N., Seshadri, G.R., Hariharan, A., Mohandas, V.P., Balasubramanian, P.: Financial market prediction using feed forward neural network. In: Communications in Computer and Information Science, pp. 77–84 (2011)
Suresh, A., Harish, K.V., Radhika, N.: Particle Swarm Optimization over back propagation neural network for length of stay prediction. Procedia Comput. Sci. 46, 268–275 (2015)
Senthil, Kumar T., Sivanandam, S.N.: An improved approach for detecting car in video using neural network model. J. Comput. Sci. 10, 1759–1768 (2012)
Padmavathi, S., Saipreethy, M.S., Valliammai, V.: Indian sign language character recognition using neural networks. Int. J. Comput. Appl. 1, 40–45 (2013)
Anil, R., Manjusha, K., Sachin Kumar, S., Soman, K.P.: Convolutional neural networks for the recognition of Malayalam characters. In: Advances in Intelligent Systems and Computing, vol. 328, pp. 493–500 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Raj, K.S., Nishanth, M., Jeyakumar, G. (2020). Design of Binary Neurons with Supervised Learning for Linearly Separable Boolean Operations. In: Smys, S., Tavares, J., Balas, V., Iliyasu, A. (eds) Computational Vision and Bio-Inspired Computing. ICCVBIC 2019. Advances in Intelligent Systems and Computing, vol 1108. Springer, Cham. https://doi.org/10.1007/978-3-030-37218-7_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-37218-7_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37217-0
Online ISBN: 978-3-030-37218-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)