5 papers
CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras
Elvin Hajizada, Michael Neumeier, Edward Paxon Frady +4
Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, bo…
The More the Merrier: Running Multiple Neuromorphic Components On-Chip for Robotic Control
Evan Eames, Priyadarshini Kannan, Ronan Sangouard +9
It has long been realized that neuromorphic hardware offers benefits for the domain of robotics such as low energy, low latency, as well as unique methods of learning. In aiming fo…
Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network
Elvin Hajizada, Danielle Rager, Timothy Shea +5
AI systems on edge devices require online continual learning -- adapting to non-stationary streams and unfamiliar classes without catastrophic forgetting -- under strict power cons…
Efficient Online Learning with Predictive Coding Networks: Exploiting Temporal Correlations
Darius Masoum Zadeh-Jousdani, Elvin Hajizada, Eyke Hüllermeier
Robotic systems operating at the edge require efficient online learning algorithms that can continuously adapt to changing environments while processing streaming sensory data. Tra…
Continual Learning for Autonomous Robots: A Prototype-based Approach
Elvin Hajizada, Balachandran Swaminathan, Yulia Sandamirskaya
Humans and animals learn throughout their lives from limited amounts of sensed data, both with and without supervision. Autonomous, intelligent robots of the future are often expec…