Weight-oriented approximation for energy-efficient neural network inference accelerators

ZG Tasoulas, G Zervakis… - … on Circuits and …, 2020 - ieeexplore.ieee.org
Current research in the area of Neural Networks (NN) has resulted in performance
advancements for a variety of complex problems. Especially, embedded system applications …

Approximate computing for ML: State-of-the-art, challenges and visions

G Zervakis, H Saadat, H Amrouch… - Proceedings of the 26th …, 2021 - dl.acm.org
In this paper, we present our state-of-the-art approximate techniques that cover the main
pillars of approximate computing research. Our analysis considers both static and …

Design automation of approximate circuits with runtime reconfigurable accuracy

G Zervakis, H Amrouch, J Henkel - IEEE access, 2020 - ieeexplore.ieee.org
Leveraging the inherent error tolerance of a vast number of application domains that are
rapidly growing, approximate computing arises as a design alternative to improve the …

Circuit-level techniques for logic and memory blocks in approximate computing systemsx

S Amanollahi, M Kamal, A Afzali-Kusha… - Proceedings of the …, 2020 - ieeexplore.ieee.org
This article presents an overview of circuit-level techniques used for approximate computing
(AC), including both computation and data storage units. After providing some background …

A cross-layer gate-level-to-application co-simulation for design space exploration of approximate circuits in HEVC video encoders

G Paim, LMG Rocha, H Amrouch… - … on Circuits and …, 2019 - ieeexplore.ieee.org
A cross-layer design space exploration (DSE) method based on a proposed co-simulation
technique is presented herein. The proposed method is demonstrated evaluating the …

Approximate computing and the efficient machine learning expedition

J Henkel, H Li, A Raghunathan, MB Tahoori… - Proceedings of the 41st …, 2022 - dl.acm.org
Approximate computing (AxC) has been long accepted as a design alternative for efficient
system implementation at the cost of relaxed accuracy requirements. Despite the AxC …

On the resiliency of NCFET circuits against voltage over-scaling

G Paim, G Zervakis, G Pahwa… - … on Circuits and …, 2021 - ieeexplore.ieee.org
Approximate computing is established as a design alternative to improve the energy
requirements of a vast number of applications, leveraging their intrinsic error tolerance …

Thermal-aware design for approximate DNN accelerators

G Zervakis, I Anagnostopoulos… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Recent breakthroughs in Neural Networks (NNs) have made DNN accelerators ubiquitous
and led to an ever-increasing quest on adopting them from Cloud to edge computing …

Model-to-circuit cross-approximation for printed machine learning classifiers

G Armeniakos, G Zervakis, D Soudris… - … on Computer-Aided …, 2023 - ieeexplore.ieee.org
Printed electronics (PEs) promises on-demand fabrication, low nonrecurring engineering
costs, and subcent fabrication costs. It also allows for high customization that would be …

Deep-PowerX: A deep learning-based framework for low-power approximate logic synthesis

G Pasandi, M Peterson, M Herrera, S Nazarian… - Proceedings of the …, 2020 - dl.acm.org
This paper aims at integrating three powerful techniques namely Deep Learning,
Approximate Computing, and Low Power Design into a strategy to optimize logic at the …