Hence it is defined as information capacity under the interpretation of cognitive capacity and set theory approach is also used to define the ANN in manner of cognitive system.
📌 3 Key Takeaways
🎯
Objective & Hypothesis:In this paper presents the structural analogy between the artificial neural net (ANN) architecture and communication system principles.
📊
Key Findings & Data:Thus, a feed forward auto-associative ANN is assumed like a communication system and the channel capacity is defined as an information measure related to the number of hidden nodes which are in one hidden layer of the neural net.
💡
Conclusion & Impact:Hence it is defined as information capacity under the interpretation of cognitive capacity and set theory approach is also used to define the ANN in manner of cognitive system.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Neural Nets · Communication Channel · Learning System
Abstract
In this paper presents the structural analogy between the artificial neural net (ANN) architecture and communication system principles. Thus, a feed forward auto-associative ANN is assumed like a communication system and the channel capacity is defined as an information measure related to the number of hidden nodes which are in one hidden layer of the neural net. Here, the channel capacity formula which is given for the communication channel is represented as information a criterion that is connected with Shannon’s entropy. Hence it is defined as information capacity under the interpretation of cognitive capacity and set theory approach is also used to define the ANN in manner of cognitive system.
Horiushkina, A., Seker, S., Korkmaz, U. (2018). A COGNITIVE APPROACH TO NEURAL NETWORK MODEL BASED ON THE COMMUNICATION SYSTEM BY AN INFORMATION CRITERIA. The Journal of Cognitive Systems, Volume: 3 Issue: 1. https://ajindex.com/articles/1552019
S. Seker, “An Analytical Approach Based on Information Theory for Neural Network Architecture”, Proceeding of the 1993 International Joint Conference on Neural Networks, vol. 1, 1993, pp. 309-312.
E. Eryurek, and B.R. Upadhyaya, “Sensor validation for power plants using adaptive backpropagation neural network”, IEEE Transactions on Nuclear Science, Vol. 37, 1990, no. 2.
G. Mirchandani, and W. Cao, “On Hidden Nodes for Neural Nets, IEEE Transactions on Circuits ans Systems, vol. 36, no. 5, 1989, pp.661-664.
R.P. Lippmann, “An Introduction to Computing with Neural Nets”, IEEE ASSP Mag., vol. 2, 1988, pp. 75-89.
D.E. Rumelhart, J.L. McClelland and PDP Research Group, “Parallel Distributed Processing, Volume 1, Explorations in the Microstructure of Cognition: Foundations”, MIT Press, 1988, pp.45-76.
C.E. Shannon, A Mathematical Theory of Communication, Bell Systems Technical Journal, vol. 27, 1948, pp. 623-656.
L. Boltzmann, (1886). "The Second Law of Thermodynamics" (pgs. 14-32; struggle quote, pg. 24, affinity and energy set free, pgs. 26-27). In B. McGinness, ed., Ludwig Boltzmann: Theoretical physics and Philosophical Problems: Selected Writings. Dordrecht, Netherlands: D. Reidel, 1974.
M. van Gerven, and S. Bohte, “Artificial Neural Networks as Models of Neural Information Processing”, Frantiers in Computational Neuroscience, vol. 11, 2017, pp. 1-2.
S. Haykin, “Cognitive Dynamic Systems”, Cambridge Univiversity Press, 2012, pp.14-42.
E. Hollnagel, “Cognitive System Porformance Measurement”, In E. Hollnagel G. Mancini, and D.D. Woods (Eds.), Intelligent Decision Aids. New York: Springer-Verlag, 1986.
E. Hollnagel, and D.D. Woods, “Cognitive System Engineering: New wine in the new bottles”, International Journal of Man-Machine Studies, vol. 18, 1983, pp. 583-600.
D.S. Chaplot, C. MacLellan, R. Salakhutdinov, amd K. Koedinger, “Learning Cognitive Models Using Neural Networks”, arXiv: 1806.080665v1, (arxiv.org/pdf/1806.08065.pdf), June 2018.
E. Eryurek, and B.R. Upadhyaya, “Sensor validation for power plants using adaptive backpropagation neural network”, IEEE Transactions on Nuclear Science, Vol. 37, 1990, no. 2.