SavedAdd your journal

Journals / Gazi Mühendislik Bilimleri Dergisi / 2017 / Cilt: 3 - Sayı: 3

A Review about Deep Learning Methods and Applications

Derin Öğrenme Yöntemleri Ve Uygulamaları Hakkında Bir İnceleme

Abdulkadir Şeker
Banu Diri
Hasan Hüseyin Balık
Pages
47–64
Publication Date
2017-12-27
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 aim of this study both explains the developments in deep learning to researchers and provides possible fields study with deep learning.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Artificial neural networks were used in the solution of many problems in the field of machine learning.
📊
Key Findings & Data:Artificial neural networks, which started to become a popular area at beginning of the 2000s, have switched from shallow networks to deep networks thanks to GPU developments.
💡
Conclusion & Impact:The aim of this study both explains the developments in deep learning to researchers and provides possible fields study with deep learning.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Derin öğrenme · Özellik mühendisliği · Yapay sinir ağları

Abstract

Artificial neural networks were used in the solution of many problems in the field of machine learning. However, in the period called "AI Winter", studies in this area have come to a halt due to especially hardware limitations and other problem. Artificial neural networks, which started to become a popular area at beginning of the 2000s, have switched from shallow networks to deep networks thanks to GPU developments. This approach has been successfully used in a wide range of fields from image processing to natural language processing, from medical applications to activity identification. In this study, it is described the history of the deep learning, methods and the implementations separated by the application areas. In addition, information has been given to the libraries used in recent years and working groups focused on deep learning. The aim of this study both explains the developments in deep learning to researchers and provides possible fields study with deep learning.

Özet

Makine öğrenmesi alanında yapay sinir ağları birçok problemin çözümünde sıklıkla kullanılmıştır. Ancak ―Yapay Zeka Kış Uykusu‖ olarak da adlandırılan dönemde başta donanımsal kısıtlamalar ve diğer problemler sebebiyle bu alandaki çalışmalar durma noktasına gelmiştir. 2000’lerin başında tekrar gözde bir alan olmaya başlayan yapay sinir ağları, GPU gelişmeleriyle birlikte sığ ağlardan derin ağlara geçiş yapmıştır. Bu yaklaşım görüntü işlemeden, doğal dil işlemeye, medikal uygulamalardan aktivite tanımaya kadar oldukça geniş bir yelpazede başarıyla kullanılmaya başlanmıştır. Bu çalışmada, derin öğrenmenin tarihçesi, kullanılan yöntemler ve uygulama alanlarına göre ayrılmış çalışmalar anlatılmıştır. Ayrıca son yıllarda kullanılan kütüphaneler ve derin öğrenme üzerine yoğunlaşan çalışma grupları hakkında da bilgiler verilmiştir. Bu çalışmanın amacı, hem araştırmacılara derin öğrenme konusundaki gelişmeleri anlatmak, hem de derin öğrenme ile çalışılacak muhtemel konuları vermektir.

🔖

Cite This Article

Şeker, A., Diri, B., Balık, H. H. (2017). A Review about Deep Learning Methods and Applications. Gazi Mühendislik Bilimleri Dergisi, Cilt: 3 - Sayı: 3, 47–64. https://ajindex.com/articles/666783

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (18)

  1. J. Schmidhuber, ―Deep learning in neural networks: An overview,‖ Neural Networks, vol. 61, pp. 85–117, 2015
  2. Y. LeCun, Y. Bengio, and G. Hinton, ―Deep learning,‖ Nature, vol. 521, pp. 436–444, 2015
  3. A. L. Blum and P. Langley, ―Selection of relevant features and examples in machine learning,‖ Artif. Intell., vol. 97, no. 1–2, pp. 245–271, Dec. 1997
  4. Y. Bengio, A. Courville, and P. Vincent, ―Representation Learning: A Review and New Perspectives,‖ IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 8, pp. 1798–1828, 2013
  5. L. Deng and D. Yu, ―Deep Learning: Methods and Applications,‖ Found. Trends® Signal Process., vol. 7, no. 3–4, pp. 197–387, 2014
  6. Y. Bengio, ―Learning Deep Architectures for AI,‖ Found. trends® Mach. Learn., vol. 2, no. 1, pp. 1–127, 2009
  7. H. A. Song and S.-Y. Lee, ―Hierarchical Representation Using NMF,‖ in International Conference on Neural Information Processing., 2013, pp. 466–473
  8. A. G. Ivakhnenko and V. G. Lapa, ―Cybernetic Predicting Devices,‖ 1966
  9. Tim Dettmers, ―Deep Learning in a Nutshell: History and Training Parallel Forall,‖ 2015. [Online]. Available: https://devblogs.nvidia.com/parallelforall/deeplearning-nutshell-history-training/. [Accessed: 20- Mar-2017]
  10. K. N. Fukushima, ―A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position.,‖ Biol. Cybern., vol. 36, no. 4, pp. 193–202, 1980
  11. Y. LeCun et al., ―Backpropagation Applied to Handwritten Zip Code Recognition,‖ Neural Comput., vol. 1, no. 4, pp. 541–551, Dec. 1989
  12. LeCun Yann, Boser B, and Denker J S, ―Handwritten Digit Recognition with a BackPropagation Network,‖ 1989
  13. G. E. Hinton, P. Dayan, B. J. Frey, and R. M. Neal, ―The wake-sleep algorithm for unsupervised neural networks,‖ Science, vol. 268, no. 5214, pp. 1158–61, May 1995
  14. S. Hochreiter and J. Schmidhuber, ―Long ShortTerm Memory,‖ Neural Comput., vol. 9, no. 8, pp. 1735–1780, Nov. 1997
  15. C. Cortes and V. Vapnik, ―Support-Vector Networks,‖ Mach. Learn., vol. 20, no. 3, pp. 273– 297, 1995
  16. I. N. Aizenberg, N. N. Aizenberg, and J. Vandewalle, ―Multiple-Valued Threshold Logic and Multi-Valued Neurons,‖ in Multi-Valued and Universal Binary Neurons, Boston, MA: Springer US, 2000, pp. 25–80
  17. G. E. Hinton, ―Learning multiple layers of representation,‖ Trends Cogn. Sci., vol. 11, no. 10, pp. 428–434, Oct. 2007
  18. D. Ciresan, A. Giusti, L. M. Gambardella, and J. Schmidhuber, ―Deep Neural Networ