Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Adversarial robustness; fisher information metric; information geometry; multi-class classification (1)
- Brain-inspired; catastrophic forgetting; class-incremental learning; Continual learning; feature distillation; feature re-consolidation; neuroscience-inspired; rehearsal-based learning strategies (1)
- Deloading control; frequency regulation; grid-forming (GFM) control; modular multilevel converter (MMC); offshore wind (OSW) (1)
Articles 1 - 3 of 3
Full-Text Articles in Engineering
Hybrid Deloading Control Strategy In Mmc-Based Wind Energy Conversion Systems For Enhanced Frequency Regulation, Jimiao Zhang, Jie Li
Hybrid Deloading Control Strategy In Mmc-Based Wind Energy Conversion Systems For Enhanced Frequency Regulation, Jimiao Zhang, Jie Li
Henry M. Rowan College of Engineering Faculty Scholarship
The growing integration of renewable energy sources, especially offshore wind (OSW), is introducing frequency stability challenges to electric power grids. This paper presents a novel hybrid deloading control strategy that enables modular multilevel converter (MMC)-based wind energy conversion systems (WECSs) to actively contribute to grid frequency regulation. This research investigates a permanent-magnet synchronous generator (PMSG)-based direct-drive configuration, sourced from the International Energy Agency’s (IEA’s) 15 MW reference turbine model. Specifically, phase-locked loop (PLL)-free grid-forming (GFM) control is employed via the grid-side converter (GSC), and DC-link voltage control is realized through the machine-side converter (MSC), both of which boost the energy …
Brain-Inspired Continual Learning: Robust Feature Distillation And Re-Consolidation For Class Incremental Learning, Hikmat Khan, Nidhal Carla Bouaynaya, Ghulam Rasool
Brain-Inspired Continual Learning: Robust Feature Distillation And Re-Consolidation For Class Incremental Learning, Hikmat Khan, Nidhal Carla Bouaynaya, Ghulam Rasool
Henry M. Rowan College of Engineering Faculty Scholarship
Artificial intelligence and neuroscience have a long and intertwined history. Advancements in neuroscience research have significantly influenced the development of artificial intelligence systems that have the potential to retain knowledge akin to humans. Building upon foundational insights from neuroscience and existing research in adversarial and continual learning fields, we introduce a novel framework that comprises two key concepts: feature distillation and re-consolidation. The framework distills continual learning (CL) robust features and rehearses them while learning the next task, aiming to replicate the mammalian brain's process of consolidating memories through rehearsing the distilled version of the waking experiences. Furthermore, the proposed …
Adversarial Robustness With Partial Isometry, Loic Shi-Garrier, Nidhal Carla Bouaynaya, Daniel Delahaye
Adversarial Robustness With Partial Isometry, Loic Shi-Garrier, Nidhal Carla Bouaynaya, Daniel Delahaye
Henry M. Rowan College of Engineering Faculty Scholarship
Despite their remarkable performance, deep learning models still lack robustness guarantees, particularly in the presence of adversarial examples. This significant vulnerability raises concerns about their trustworthiness and hinders their deployment in critical domains that require certified levels of robustness. In this paper, we introduce an information geometric framework to establish precise robustness criteria for (Formula presented.) white-box attacks in a multi-class classification setting. We endow the output space with the Fisher information metric and derive criteria on the input–output Jacobian to ensure robustness. We show that model robustness can be achieved by constraining the model to be partially isometric around …