Cognitive approach to support dynamic aging compensation
| Autor: | David Meyer, Abhishek Jain, S. Mhira, Chittoor Parthasarathy, Vincent Huard, Florian Cacho, S. Naudet, Alain Bravaix, A. Benhassain |
|---|---|
| Přispěvatelé: | Institut des Matériaux, de Microélectronique et des Nanosciences de Provence (IM2NP), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), STMicroelectronics [Crolles] (ST-CROLLES), Yncréa Méditerrané |
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
NBTI Computer science control loop 02 engineering and technology Compensation (engineering) [SPI]Engineering Sciences [physics] 020901 industrial engineering & automation Control theory adaptive resonance theory 0202 electrical engineering electronic engineering information engineering timing degradation energy efficiency Digital electronics business.industry Cognition in-situ monitors DTM machine learning Adaptive resonance theory Control system Unsupervised learning 020201 artificial intelligence & image processing business adaptive voltage scaling Degradation (telecommunications) |
| Zdroj: | ITC 2017 IEEE International Test Conference (ITC) 2017 IEEE International Test Conference (ITC), Oct 2017, Fort Worth, France. pp.1-7, ⟨10.1109/TEST.2017.8242042⟩ |
| Popis: | International audience; This paper shows new insights on the stochastic nature of aging-related timing impact in digital circuits. Varying critical paths through aging trigger the need for aging compensation control loop based on an unsupervised machine learning algorithm. Adaptive Resonance Theory (ART) algorithm is favored for its ability to handle the stability-plasticity dilemma. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|