Adaptive HTF-MPR
| Autor: | Ahmad Albaqsami, Masoomeh Jasemi, Nader Bagherzadeh, Maryam S. Hosseini |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Speedup
Artificial neural network Computer science business.industry Bayesian optimization Machine learning computer.software_genre Theoretical Computer Science Artificial Intelligence Softmax function Graph (abstract data type) Resource allocation Applications of artificial intelligence Artificial intelligence business computer MNIST database |
| Zdroj: | ACM Transactions on Intelligent Systems and Technology. 11:1-25 |
| ISSN: | 2157-6912 2157-6904 |
| DOI: | 10.1145/3396949 |
| Popis: | Deep neural networks are widely used in many artificial intelligence applications. They have demonstrated state-of-the-art accuracy on many artificial intelligence tasks. For this high accuracy to occur, deep neural networks require the right parameter values. This is achieved by a process known as training . The training of large amounts of data via many iterations comes at a high cost in regard to computation time and energy. Optimal resource allocation would therefore reduce the training time. TensorFlow, a computational graph library developed by Google, alleviates the development of neural network models and provides the means to train these networks. In this article, we propose Adaptive HTF-MPR to carry out the resource allocation, or mapping, on TensorFlow. Adaptive HTF-MPR searches for the best mapping in a hybrid approach. We applied the proposed methodology on two well-known image classifiers: VGG-16 and AlexNet. We also performed a full analysis of the solution space of MNIST Softmax. Our results demonstrate that Adaptive HTF-MPR outperforms the default homogeneous TensorFlow mapping. In addition to the speed up, Adaptive HTF-MPR can react to changes in the state of the system and adjust to an improved mapping. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|