ALOHA
Autor: | Meloni, P., Loi, D., Deriu, G., Pimentel, A.D., Sapra, D., Moser, B., Shepeleva, N., Conti, F., Benini, L., Ripolles, O., Solans, D., Pintor, M., Biggio, B., Stefanov, T., Minakova, S., Fragoulis, N., Theodorakopoulos, I., Masin, M., Palumbo, F., Martina, M., Fornanciari, W. |
---|---|
Přispěvatelé: | System and Network Engineering (IVI, FNWI), Meloni, P. and Loi, D. and Deriu, G. and Pimentel, A. D. and Sapra, D. and Moser, B. and Shepeleva, N. and Conti, F. and Benini, L. and Ripolles, O. and Solans, D. and Pintor, M. and Biggio, B. and Stefanov, T. and Minakova, S. and Fragoulis, N. and Theodorakopoulos, I. and Masin, M. and Palumbo, F. |
Rok vydání: | 2018 |
Předmět: |
010302 applied physics
Process (engineering) Computer science business.industry Deep learning Distributed computing Inference Cloud computing 02 engineering and technology computer aided design convolutional neural networks deep learning 01 natural sciences Porting Software Aloha 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Enhanced Data Rates for GSM Evolution Artificial intelligence business |
Zdroj: | INTESA@ESWEEK INTelligent Embedded Systems Architectures and Applications (INTESA): workshop proceedings 2018 : October 4, 2018, Torino, Italy, 19-26 STARTPAGE=19;ENDPAGE=26;TITLE=INTelligent Embedded Systems Architectures and Applications (INTESA) Proceedings of the Workshop on INTelligent Embedded Systems Architectures and Applications-INTESA 18 Proceedings of the Workshop on INTelligent Embedded Systems Architectures and Applications -INTESA '18 |
Popis: | Novel Deep Learning (DL) algorithms show ever-increasing accuracy and precision in multiple application domains. However, some steps further are needed towards the ubiquitous adoption of this kind of instrument. First, effort and skills required to develop new DL models, or to adapt existing ones to new use-cases, are hardly available for small- and medium-sized businesses. Second, DL inference must be brought at the edge, to overcome limitations posed by the classically-used cloud computing paradigm. This requires implementation on low-energy computing nodes, often heterogenous and parallel, that are usually more complex to program and to manage. This work describes the ALOHA framework, that proposes a solution to these issue by means of an integrated tool flow that automates most phases of the development process. The framework introduces architecture-awareness, considering the target inference platform very early, already during algorithm selection, and driving the optimal porting of the resulting embedded application. Moreover it considers security, power efficiency and adaptiveness as main objectives during the whole development process. |
Databáze: | OpenAIRE |
Externí odkaz: |