Report
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
| العنوان: | MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks |
|---|---|
| المؤلفون: | Gordon, Ariel, Eban, Elad, Nachum, Ofir, Chen, Bo, Wu, Hao, Yang, Tien-Ju, Choi, Edward |
| سنة النشر: | 2017 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Computer Science - Learning, Statistics - Machine Learning |
| الوصف: | We present MorphNet, an approach to automate the design of neural network structures. MorphNet iteratively shrinks and expands a network, shrinking via a resource-weighted sparsifying regularizer on activations and expanding via a uniform multiplicative factor on all layers. In contrast to previous approaches, our method is scalable to large networks, adaptable to specific resource constraints (e.g. the number of floating-point operations per inference), and capable of increasing the network's performance. When applied to standard network architectures on a wide variety of datasets, our approach discovers novel structures in each domain, obtaining higher performance while respecting the resource constraint. Comment: Added reproducibility and stability figures in the appendix, as well minor typos and clarifications to the main text |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/1711.06798 |
| رقم الانضمام: | edsarx.1711.06798 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |