Improving the performance of deep neural networks by clustering
Publish place: 2rd International Conference on Soft Computing
Publish Year: 1396
نوع سند: مقاله کنفرانسی
زبان: English
View: 447
This Paper With 9 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
CSCG02_111
تاریخ نمایه سازی: 7 اسفند 1396
Abstract:
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
Keywords:
Authors
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