137 citations · 511 across the 22 of their papers we have counts for
10 papers · 1 filter
Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey
Kilian Pfeiffer, Martin Rapp, Ramin Khalili +1
With an increasing number of smart devices like internet of things (IoT) devices deployed in the field, offloadingtraining of neural networks (NNs) to a central server becomes more…
Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices
Kilian Pfeiffer, Ramin Khalili, Jörg Henkel
Federated learning (FL) is usually performed on resource-constrained edge devices, e.g., with limited memory for the computation. If the required memory to train a model exceeds th…
Model-to-Circuit Cross-Approximation For Printed Machine Learning Classifiers
Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris +2
Printed electronics (PE) promises on-demand fabrication, low non-recurring engineering costs, and sub-cent fabrication costs. It also allows for high customization that would be in…
Co-Design of Approximate Multilayer Perceptron for Ultra-Resource Constrained Printed Circuits
Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris +2
Printed Electronics (PE) exhibits on-demand, extremely low-cost hardware due to its additive manufacturing process, enabling machine learning (ML) applications for domains that fea…
Energy-efficient DNN Inference on Approximate Accelerators Through Formal Property Exploration
Ourania Spantidi, Georgios Zervakis, Iraklis Anagnostopoulos +1
Deep Neural Networks (DNNs) are being heavily utilized in modern applications and are putting energy-constraint devices to the test. To bypass high energy consumption issues, appro…
Cross-Layer Approximation For Printed Machine Learning Circuits
Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris +2
Printed electronics (PE) feature low non-recurring engineering costs and low per unit-area fabrication costs, enabling thus extremely low-cost and on-demand hardware. Such low-cost…
CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization
Kilian Pfeiffer, Martin Rapp, Ramin Khalili +1
Devices participating in federated learning (FL) typically have heterogeneous communication, computation, and memory resources. However, in synchronous FL, all devices need to fini…
AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorch
Dimitrios Danopoulos, Georgios Zervakis, Kostas Siozios +2
Current state-of-the-art employs approximate multipliers to address the highly increased power demands of DNN accelerators. However, evaluating the accuracy of approximate DNNs is…
DISTREAL: Distributed Resource-Aware Learning in Heterogeneous Systems
Martin Rapp, Ramin Khalili, Kilian Pfeiffer +1
We study the problem of distributed training of neural networks (NNs) on devices with heterogeneous, limited, and time-varying availability of computational resources. We present a…
Control Variate Approximation for DNN Accelerators
Georgios Zervakis, Ourania Spantidi, Iraklis Anagnostopoulos +2
In this work, we introduce a control variate approximation technique for low error approximate Deep Neural Network (DNN) accelerators. The control variate technique is used in Mont…