Towards a learning-based performance modeling for accelerating Deep Neural Networks
| Autor: | Damiano Perri, Osvaldo Gervasi, Sergio Tasso, Paolo Sylos Labini, Flavio Vella |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Optimization Computer Science - Machine Learning Optimization Deep Learning Convolutional Neural Networks Computer science Decision tree 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Convolution Machine Learning (cs.LG) Deep Learning 0105 earth and related environmental sciences Artificial neural network business.industry Deep learning 05 social sciences Convolutional Neural Networks 050301 education Range (mathematics) Deep neural networks Artificial intelligence Focus (optics) business 0503 education computer |
| Zdroj: | Computational Science and Its Applications – ICCSA 2019 ISBN: 9783030242886 ICCSA (1) |
| Popis: | Emerging applications such as Deep Learning are often data-driven, thus traditional approaches based on auto-tuners are not performance effective across the wide range of inputs used in practice. In the present paper, we start an investigation of predictive models based on machine learning techniques in order to optimize Convolution Neural Networks (CNNs). As a use-case, we focus on the ARM Compute Library which provides three different implementations of the convolution operator at different numeric precision. Starting from a collation of benchmarks, we build and validate models learned by Decision Tree and naive Bayesian classifier. Preliminary experiments on Midgard-based ARM Mali GPU show that our predictive model outperforms all the convolution operators manually selected by the library. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|