3 papers
cs.AR2024
Energy-Aware Heterogeneous Federated Learning via Approximate DNN Accelerators
Kilian Pfeiffer, Konstantinos Balaskas, Kostas Siozios +1
In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do…
cs.AR2024
Bespoke Approximation of Multiplication-Accumulation and Activation Targeting Printed Multilayer Perceptrons
Florentia Afentaki, Gurol Saglam, Argyris Kokkinis +3
Printed Electronics (PE) feature distinct and remarkable characteristics that make them a prominent technology for achieving true ubiquitous computing. This is particularly relevan…
cs.AR2024
Evolutionary Approximation of Ternary Neurons for On-sensor Printed Neural Networks
Vojtech Mrazek, Argyris Kokkinis, Panagiotis Papanikolaou +5
Printed electronics offer ultra-low manufacturing costs and the potential for on-demand fabrication of flexible hardware. However, significant intrinsic constraints stemming from t…