The week's pick
Random Articles
Reseach Article
Use of Activation Values and Weight Space by Activation and Synaptic Dynamics for Network Reliability Measurement
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 176 - Number 14 |
| Year of Publication: 2020 |
| Authors: Anuradha, Harish Kumar, Rakesh Kumar Arora |
10.5120/ijca2020920046
|
Anuradha, Harish Kumar, Rakesh Kumar Arora . Use of Activation Values and Weight Space by Activation and Synaptic Dynamics for Network Reliability Measurement. International Journal of Computer Applications. 176, 14 ( Apr 2020), 7-11. DOI=10.5120/ijca2020920046
Abstract
The problem which is occurring nowadays for networks is reliability as the networks are becoming more wide and complex. Reliability is the ability of a network to carry out a desired operation such as "communication”. It is one of the most important aspects of networks for solving complex problems. The network should have minimum failure and should be cost-effective. The solution can be attained by using artificial neural network. An Artificial Neural Network is a highly simplified model of the structure of the biological neural network. It consists of interconnected processing units. The weight present between the connections is used for activation value. The inputs or outputs of the artificial neural networks could be discrete or continuous and also could be deterministic or stochastic. The activation dynamics determine the activation values of nodes. Synaptic dynamics is to adjust the weights in order to store given patterns in the network. This paper presents different measures of the reliability of the network by using Artificial Neural Network. The evaluation of the network is been done by studying various approaches to reliability measurement. The aim of the work is to present an optimized neural network approach to improve reliability with a high learning rate.
References
- D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning internal representation by error propagation,” in Parallel Distributed Processing: Exploration in the Microstructure of Cognition. Cambridge,Massachusetts: MIT Press, 1986, vol. I, pp. 318–361.
- Misha Tsodyks, Klaus Pawelzik, Henry Markram, “Neural Networks with Dynamic Synapses” Neural Computation, MIT 10, 821–835 (1998)
- Abdullah Konak and Alice E “Designing Resilient Networks Using a Hybrid Genetic Algorithm Approach” GECCO’05, June 25-29, 2005, Washington, DC, USA. Copyright 2005 ACM 1-59593-010-8/05/0006
- T. Elperin, I. Gertsbakh, M. Lomonosov, “An evolution model for Monte Carlo estimation of equilibrium network renewal parameters”, Prob. Eng. Inf. Sci. 6(1992) 457–469.
- Bibitchkov D., Herrmann J. M., Geisel T. (2002). Pattern storage and processing in attractor networks with short-time synaptic dynamics. Netw. Comput. Neural Syst. 13, 115–129
- Y. Shpungin, “Combinatorial approaches to Monte Carlo estimation of dynamic systems reliability parameters,” Comm. Depend. Qual. Manage. 9 (1) (2006)69–75.
- Ramanathan, C.J. Colbourn, “Counting almost minimum cut sets with reliability” applications, Math. Program. 39 (2005) 253–261.
- Anuradha and Anil Kumar “Calculation and Evaluation of Network Reliability using ANN Approach” International Conference on Computational Intelligence and Data Science (ICCIDS 2019), Northcap University, India
- Zhongshi He, Yufang Tian, Yinong Chen,“Simulating the reliability of Distributed systems with unreliable nodes” ijssst.info/Vol-03/No-1&2
- Yegnanarayana . B, “Artificial Neural Network” 2009, 461p.ISBN 8120312538
- Bonifazi P., Ruaro M. E., Torre V. (2005). Statistical properties of information processing in neuronal networks. Eur. J. Neurosci. 22, 2953–2964
- Wang XJ(2008) Decision making in recurrent neuronal circuits. Neuron 60:215–234
- Mongillo G,Barak O,Tsodvks (2008) Synaptic theory of working memory Science319:1543–1546.
- Joaquin J. Torres and Hilbert J. Kappen “Emerging phenomena in neural networks with dynamic synapses and their computational implications” Front Comput Neurosci. 2013; 7: 30.
- Kilpatrick Z. P., Bressloff P. C. (2010). Spatially structured oscillations in a two-dimensional excitatory neuronal network with synaptic depression. J. Comput. Neurosci. 28, 193–209 10.1007/s10827-009-0199-6
- Barak O., Tsodyks M. (2007). Persistent activity in neural networks with dynamic synapses. PLoS Comput. Biol 3:e35 10.1371/journal.pcbi.0030035
- Schalkoff Robert J., “Artificial Neural Network”, 1997, 421p. ISBN 0-07-115554-6
- Mazzoni A., Broccard F. D., Garcia-Perez E., Bonifazi P., Ruaro M. E., Torre V. (2007). On the dynamics of the spontaneous activity in neuronal networks. PLoS ONE 2:e439 10.1371/journal.pone.0000439
- Collins J. J., Carson Chow C. C., Imhoff T. T. (1995). Aperiodic stochastic resonance in excitable systems. Phys. Rev. E 52, R3321–R3324 10.1103/PhysRevE.52.R3321
- Krahe R, Gabbiani F (2004) Burst firing in sensory systems. Nat Rev Neurosci 5: 13–23
- Duda Richard O. , Hart Peter E., Stork David G. “Pattern Classification” Wiley Student Edition ISBN: 978-81-265-1116-7,654p.
- Yasuda H., Miyaoka T., Horiguchi J., Yasuda A., Hanggi P., Yamamoto Y. (2008). Novel class of neural stochastic resonance and error-free information transfer. Phys. Rev. Lett. 100:118103 10.1103/PhysRevLett.100.118103
Index Terms
Keywords