FEED-FORWARD NEURAL NETWORKS REGRESSION ANALYSIS WITH GENETIC ALGORITHMS: APPLICATIONS IN ECONOMICS AND FINANCE
Öz
In this paper feed-forward neural networks are examined using
genetic algorithms in the training process instead of error backpropagation
algorithm. Additionally, real encoding is preferred to binary encoding as it is
more appropriate to find the optimum weights. Learning and momentum rates are
used for the weight updating as in the case of the error backpropagation
algorithm. Some empirical examples as well as the programming routines in
MATLAB are provided in the paper.
Anahtar Kelimeler
Feed-Forward Neural Networks Genetic Algorithms Time-Series Stock Returns Inflation Rate Gross Domestic Product Forecasting
Kaynakça
- Antonisse, J. (1989), “A new interpretation of schema notation that overturns the binary encoding constraint”, In J. D. Schaffer, ed., Proceedings of the Third International Conference on Genetic Algorithms, pp. 86-91, George Mason University, USA
- Bäck, T. (1996), Evolutionary Algorithms in Theory and Practice. Oxford University Press
- Janikow, C. Z. and Michalewicz, Z. (1991), “An experimental comparison of binary and floating point representations in genetic algorithms”, In R. K. Belew and L. B. Booker, eds., Proceedings of the Fourth International Conference on Genetic Algorithms, Morgan Kaufmann Publishers
- Mitchell, M. (1996), “An Introduction to Genetic Algorithms”, MIT Press Cambridge, Massachusetts, London, England.
- Nelson, D.B. (1991), “Conditional Heteroskedasticity In Asset Returns: A New Approach”, Econometrica, 59,(2): 347-370.
- Wright, A. H. (1991). Genetic algorithms for real parameter optimization. In G. Rawlins, ed., Foundations of Genetic Algorithms, Morgan Kaufmann Publishers
GENETİK ALGORİTMALAR İÇEREN İLERİ BESLEMELİ SİNİR AĞLARI REGRESYON ANALİZLERİ: İKTİSAT VE FİNANS ALANINDA UYGULAMALAR
Öz
Bu çalışmada ileri beslemeli sinir
ağları, hata geriye yayma algoritması yerine öğrenme sürecinde genetik
algoritmalar kullanılarak incelenmiştir. İlave olarak, optimal ağırlıkları
bulmada daha uygun olduğundan ikil kodlama yerine gerçek kodlamanın kullanımı
tercih edilmiştir. Hata geriye yayma algoritmasında olduğu gibi ağırlıkların
güncellenmesi için öğrenme ve momentum katsayıları kullanılmıştır. MATLAB’da
yapılan ampirik örnekler ve program yordamları çalışmada sunulmuştur.
Anahtar Kelimeler
İleri Beslemeli Sinir Ağları Genetik Algoritmalar Zaman Serileri Hisse Senedi Getirileri Enflasyon Oranı Yurtiçi Hasıla Kestirim
Kaynakça
- Antonisse, J. (1989), “A new interpretation of schema notation that overturns the binary encoding constraint”, In J. D. Schaffer, ed., Proceedings of the Third International Conference on Genetic Algorithms, pp. 86-91, George Mason University, USA
- Bäck, T. (1996), Evolutionary Algorithms in Theory and Practice. Oxford University Press
- Janikow, C. Z. and Michalewicz, Z. (1991), “An experimental comparison of binary and floating point representations in genetic algorithms”, In R. K. Belew and L. B. Booker, eds., Proceedings of the Fourth International Conference on Genetic Algorithms, Morgan Kaufmann Publishers
- Mitchell, M. (1996), “An Introduction to Genetic Algorithms”, MIT Press Cambridge, Massachusetts, London, England.
- Nelson, D.B. (1991), “Conditional Heteroskedasticity In Asset Returns: A New Approach”, Econometrica, 59,(2): 347-370.
- Wright, A. H. (1991). Genetic algorithms for real parameter optimization. In G. Rawlins, ed., Foundations of Genetic Algorithms, Morgan Kaufmann Publishers
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Bölüm | Makaleler |
| Yazarlar | |
| Yayımlanma Tarihi | 14 Haziran 2018 |
| Yayımlandığı Sayı | Yıl 2018 Cilt: 3 Sayı: 1 |
