A quality-aware voltage overscaling framework to improve the energy efficiency and lifetime of TPUs based on statistical error modeling

A Senobari, J Vafaei, O Akbari, C Hochberger… - IEEE …, 2024 - ieeexplore.ieee.org
Deep neural networks (DNNs) are a type of artificial intelligence models that are inspired by
the structure and function of the human brain, designed to process and learn from large …

HPR-Mul: An Area and Energy-Efficient High-Precision Redundancy Multiplier by Approximate Computing

J Vafaei, O Akbari - IEEE Transactions on Very Large Scale …, 2024 - ieeexplore.ieee.org
For critical applications that require a higher level of reliability, the triple modular
redundancy (TMR) scheme is usually employed to implement fault-tolerant arithmetic units …

Design Exploration of Fault-Tolerant Deep Neural Networks Using Posit Number Representation System

M Yousefloo, O Akbari - IEEE Transactions on Very Large Scale …, 2024 - ieeexplore.ieee.org
The applications of deep neural networks (DNNs) in different safety-critical systems (such as
autonomous vehicles and robotics) are experiencing emerging growth due to their high …

Reconfigurable Approximating Accelerators for Edge Computing

HJ Damsgaard - 2024 - trepo.tuni.fi
Edge computing is one of the key technologies for tackling the growing rate of data
production and connectivity demands in Internet of Things (IoT) devices. Distributed edge …

[引用][C] Design and Analysis of Optimized Approximate Multiplier Using Novel Higher-Order Compressor

G Thakur, S Jain - Journal of Circuits, Systems and Computers, 2024 - World Scientific
The energy-efficient error-tolerant circuits have paved the way for a whole new area in low-
power consumption applications with approximate computing. The approximate computing …