Improving the performance of deep neural networks by clustering

  • سال انتشار: 1396
  • محل انتشار: دومین کنفرانس ملی محاسبات نرم
  • کد COI اختصاصی: CSCG02_111
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 452
دانلود فایل این مقاله

نویسندگان

Saeedeh Khaleghi

Masters student of Algorithms and Computation, University of Tehran, School of Engineering Science, Department of Algorithms and Computation, Tehran, Iran

Mahmood Shabankhah

Assistant Professor, University of Tehran, School of Engineering Science, Department of Algorithms and Computation, Tehran, Iran

چکیده

Neural networks applications have been widely employed in many of today’s intelligent systems, especially in embedded systems and smart phones. This trend brings with itself many challenges, one of which is the effective handling of large numbers of parameters given the limited size of available memory in such systems. Indeed, networks with high number of adjustable parameters are generally prone to overfitting. A common approach in such cases would be to downsize the network. In this paper, we use clustering to meet this goal. Indeed, we cluster the weights in each layer into a smaller number of groups. In parallel, the network architecture is accordingly modified. The main part of the training procedure is done on this smaller network. Therefore, the training time will be greatly improved. Finally, the initial network’s weights will eventually be reconstructed from the weights obtained in the last step. The most important feature of our approach is that although the training is faster but the performance of the network does not suffer

کلیدواژه ها

Deep neural networks, K-means clustering, learning speed, overfitting

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.