Convolutional Neural Networks: Challenges and Trends

سال انتشار: 1395
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 833

فایل این مقاله در 8 صفحه با فرمت PDF قابل دریافت می باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

ELECONFK03_135

تاریخ نمایه سازی: 11 مرداد 1396

چکیده مقاله:

Convolutional neural network has gained enormous success in recent years, and is one of the most popular deep learning algorithms that has been extensively used in many machine learning related fields. The success and different applications of CNN have been studied and addressed in many studies in the literature, however, some aspects which interestingly are very important are either less worked on or ignored completely. In this paper we study and address some of the aspects and respective trends that affect the application of CNN in various fields.

نویسندگان

Seyyed Hossein Hasanpour

Department of Computer Science IAU. Science and research branch of Ayatollah Amoli Amol, Iran

Reza Saadati

Department of Mathematics Iran University of Science and Technology Noor, Iran

مراجع و منابع این مقاله:

لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :
  • Schmidhuber, J., Deep learning in neural networks: An overview. Neural ...
  • Bengio, Y., Deep Learning of Represen tations: Looking Forward, in ...
  • Mahendran, A. and A. Vedaldi. Understa nding deep image represen ...
  • Mahendran, A. and A. Vedaldi, Visualizing deep convolutional neural networks ...
  • Zhou, B., et al., Object detectors emerge in deep scene ...
  • Agrawal, P., R. Girshick, and J. Malik, Analyzing the performance ...
  • HasanPour, S.H., et al., Lets keep it simple: using simple ...
  • He , K., et al., Deep Residual Learning for Image ...
  • Szegedy, C., et al. Going deeper with convolutions. in Proceedings ...
  • Cadieu, C.F., et al., Deep neural networks rival the represen ...
  • Iandola, F.N., et al., SqueezeNet: AlexNet-level accuracy with 50x fewer ...
  • Wu, R., et al., Deep image: Scaling up image recognition. ...
  • Divvala, S., A. Farhadi, and C. Guestrin. Learning everything about ...
  • Zhou, B., V. Jagadeesh, and R. Piramuthu. Concep tlearner: Discovering ...
  • Editors. 2013, Springer Berlin Heidelberg: Berlin, Heidelberg. p. 1-37. ...
  • Bengio, Y., Learning Deep Architectures for AI. Found. Trends Mach. ...
  • Bengio, Y.a.C., A. and Vincent, P., R epresentation Learning: A ...
  • Deng, L., A tutorial survey _ architectures, algorithms, and applications ...
  • LeCun, Y., et al., Gradien t-based learning applied to document ...
  • Krizhevsky, A., I. Sutskever, and G.E. Hinton. Imagenet classification with ...
  • Girshick, R., Fast R-CNN. The IEEE International Conference on Computer ...
  • LeCun, Y., Y. Bengio, and G. Hinton, Deep learring. Nature, ...
  • Fukushima, K., Neural Network Model for a Mechanism of Pattern ...
  • Hubel, D.H. and T.N. Wiesel, Receptive fields, binocular interaction and ...
  • Yu, W., et al., Visualizing and Comparing Convolutional Neural Networks. ...
  • Mordvintsev, A., C. Olah, and M. Tyka, Inceptionism: Going deeper ...
  • Radford, A., L. Metz, and S. Chintala, Unsupervised representation learning ...
  • He, K. and J. Sun. Con volutional neural networks at ...
  • Ba, J. and R. Caruana. Do deep nets really need ...
  • Han, S., H. Mao, and W.J. Dally, Deep compression: Compressing ...
  • Huang, G., Z. Liu, and K.Q. Weinberger, Densely Connected Convolutional ...
  • Goodfellow, I.J., J. Shlens, and C. Szegedy, Explaining and harnessing ...
  • Nguyen, A., J. Yosinski, and J. Clune. Deep neural networks ...
  • Szegedy, C., et al., Intriguing properties of neural networks. arXiv ...
  • Tatu, A., et al. Exploring the representation capabilities of the ...
  • نمایش کامل مراجع