Journals / Karaelmas Fen ve Mühendislik Dergisi / 2016 / Cilt: 6 - Sayı: 1

Impact of Newman-Watts Small-World approach on The Performance of Feed-Forward Artificial Neural Networks

Newman-Watts Küçük Dünya Yaklaşımının İleri Yönlü Yapay Sinir Ağları Performansına Etkisi

Pages
187–194
Publication Date
2016-01-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The obtained results show that the values of output error and determination coefficient of the network by the Newman-Watts SW approach are the better than those of the regular network, leading to the fact that the performance of Newman-Watts network is better than the regular networks.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In the Feed Forward Neural Network FFANN , performance of the learning changes with training algorithm, structure of hidden layer and number of neurons within the layers.
📊
Key Findings & Data:Therefore, many research are conducted to improve the performance of network, and different approaches are suggested to achieve it.
💡
Conclusion & Impact:The obtained results show that the values of output error and determination coefficient of the network by the Newman-Watts SW approach are the better than those of the regular network, leading to the fact that the performance of Newman-Watts network is better than the regular networks.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:İleri yönlü yapay sinir ağları · Newman-Watts küçük dünya ağları · Öğrenme performansı

Abstract

In the Feed Forward Neural Network FFANN , performance of the learning changes with training algorithm, structure of hidden layer and number of neurons within the layers. Therefore, many research are conducted to improve the performance of network, and different approaches are suggested to achieve it. In this study, we analyse the impact of Newman-Watts Small-World SW approach on the performance of the FFANN. The obtained results show that the values of output error and determination coefficient of the network by the Newman-Watts SW approach are the better than those of the regular network, leading to the fact that the performance of Newman-Watts network is better than the regular networks. In this way, similar to the Watts-Strogatz FFANNs, it is shown that the Newman-Watts FFANNs can be used to solve black-box problem of ANN studies in the future.

Özet

İleri yönlü yapay sinir ağlarında, öğrenme performansı; öğrenme algoritması, ara katman yapısı ve katmanlardaki nöron sayısına bağlı olarak değişim göstermektedir. Bu nedenle, ağ performansını artırabilmek için araştırmalar yapılmakta ve farklı yaklaşımlar önerilmektedir. Bu çalışmada, Newman-Watts bağlantı yenileme yaklaşımı kullanılarak tasarlanan Küçük-Dünya SW ağ modelinin ileri yönlü yapay sinir ağı FFANN performansına etkisi incelenmiştir. Elde edilen sonuçlar düzenli ağ topolojisine göre SW ağ topolojisinin çıkış hata ve belirtme katsayısı değerlerinin daha iyi olduğunu, sonuç olarak, Newman-Watts SW ağının öğrenme performansının düzenli ağa göre daha iyi olduğunu göstermektedir. Böylece, Watts-Strogatz SW ağlarında olduğu gibi Newman-Watts SW ağlarının da, gelecekteki yapay sinir ağ çalışmalarının kara-kutu problemine bir çözüm olarak kullanılabileceği vurgulanmıştır

🔖

Cite This Article

ERKAYMAZ, O., ÖZER, M. (2016). Impact of Newman-Watts Small-World approach on The Performance of Feed-Forward Artificial Neural Networks. Karaelmas Fen ve Mühendislik Dergisi, Cilt: 6 - Sayı: 1, 187–194. https://ajindex.com/articles/684075

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (11)

  1. barabasi, AL., Albert, R. 1999. Emergence of Scaling in Random Networks. Science, 286: 509-512. bassett, DS., bullmore, E. 2006. Small-world brain networks. The Neuroscientist 12: (6): 512-523. buhmann, Martin D. 2003. Radial Basis Functions: Theory and implementations, Cambridge University Press, 259 pp. Camacho, J., Guimerà, R., Nunes Amaral LA. 2002. Robust patterns in food web structure. Phys. Rev. Let., 88: 228102-1-4.
  2. Caner, M., Gedik, E., Keçebaş, A. 2011. Investigation on thermal performance calculation of two type solar air collectors using artificial neural network. Exp. Sys. W. App., 38(3): 1668-1674.
  3. Erkaymaz O., Ozer M, Yumusak N. 2014. Impact of small-world topology on the performance of a feed-forward artificial neural network based on 2 different real-life problems. Turk. J. Elec. Eng. and Comp. Sci., 22: 708-718.
  4. Erkaymaz, O., Ozer, M. 2016. Impact of small-world network topology on the conventional artiŞcial neural network for the diagnosis of diabetes. Chaos Sol. and Fract., 83: 178-185.
  5. Gurney, K. 2002.
  6. An Introduction to Neural Networks, Routledge, UCL Press, 248 pp. Haykin, S. 1999. Neural Networks—A Comprehensive Foundation, 2nd Edition,
  7. Prentice-Hall, Englewood Cliffs, NJ, 936 pp. Jeong, H., Mason, SP., barabási, AL., Oltvai, ZN. 2001. Lethality and centrality in protein networks. Nature, 411:41- 42. Latora, V., Marchiori, M. 2001. Efficient behavior of small-world networks. Phys. Rev. Let., 87:198701. Latora, V., Marchiori, M. 2003. Economic small-world behavior in weighted networks. Eur. Phys J. B, 32: 249–263.
  8. Magnitskii, NA. 2001. Some New Approaches to the Construction and Learning of Artificial neural Networks. Comp. Math. and Mod., 12(4):293-304.
  9. Newman, ME. J, Watts. DJ. 1999. Scaling and percolation in the small-world network model. Phys. Rev. E, 60: 7332-7342. ve Erkaymaz ve Ozer (2016) tarafından düzenli FFANN TS EN 310 1999. Wood-Based panels-Determination of modulus of elasticity and of bending strength, TSE, Ankara.
  10. Watts, DJ., Strogatz, SH. 1998. Collective dynamics of small- world networks, Nature, 393: 409-10.
  11. Watts, DJ. 2003. Small Worlds: The Dynamics of Networks Between Order and Randomness, Princeton, Princeton University Press, NJ, 280 pp. Yapıcı, F. 2008. The effect of some production factors on the properties of osb made from scotch pine (pinus sylvestris l.) wood. Doktora Tezi, Zonguldak Karaelmas Üniversitesi,143 s. Yılmaz, E., Uzuntarla, M., Ozer, M., Perc, M. 2013. Stochastic resonance in hybrid scale-fre