تقرير
Efficient Differentiable Programming in a Functional Array-Processing Language
| العنوان: | Efficient Differentiable Programming in a Functional Array-Processing Language |
|---|---|
| المؤلفون: | Shaikhha, Amir, Fitzgibbon, Andrew, Vytiniotis, Dimitrios, Jones, Simon Peyton, Koch, Christoph |
| سنة النشر: | 2018 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Computer Science - Mathematical Software, Computer Science - Learning, Computer Science - Programming Languages, Computer Science - Symbolic Computation, Statistics - Machine Learning |
| الوصف: | We present a system for the automatic differentiation of a higher-order functional array-processing language. The core functional language underlying this system simultaneously supports both source-to-source automatic differentiation and global optimizations such as loop transformations. Thanks to this feature, we demonstrate how for some real-world machine learning and computer vision benchmarks, the system outperforms the state-of-the-art automatic differentiation tools. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/1806.02136 |
| رقم الأكسشن: | edsarx.1806.02136 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |