Testability and dependability of AI hardware: Survey, trends, challenges, and perspectives
F Su, C Liu, HG Stratigopoulos - IEEE Design & Test, 2023 - ieeexplore.ieee.org
Hardware realization of artificial intelligence (AI) requires new design styles and even
underlying technologies than those used in traditional digital processors or logic circuits …
underlying technologies than those used in traditional digital processors or logic circuits …
NEAT: Nonlinearity aware training for accurate, energy-efficient, and robust implementation of neural networks on 1T-1R crossbars
In this era of IoT, energy-efficient and adversarially secure implementation of deep neural
networks (DNNs) on hardware has become imperative. Memristive crossbars have emerged …
networks (DNNs) on hardware has become imperative. Memristive crossbars have emerged …
Unary coding and variation-aware optimal mapping scheme for reliable ReRAM-based neuromorphic computing
Neural network (NN) computing contains a large number of multiply-and-accumulate (MAC)
operations. The performance of NN accelerator is limited with the traditional von Neumann …
operations. The performance of NN accelerator is limited with the traditional von Neumann …
R2F: A remote retraining framework for AIoT processors with computing errors
Artificial Intelligence of Things (AIoT) processors fabricated with newer technology nodes
suffer rising soft errors due to the shrinking transistor sizes and lower power supply. Soft …
suffer rising soft errors due to the shrinking transistor sizes and lower power supply. Soft …
Mapping-aware biased training for accurate memristor-based neural networks
S Diware, A Gebregiorgis, RV Joshi… - 2023 IEEE 5th …, 2023 - ieeexplore.ieee.org
Memristor-based computation-in-memory (CIM) can achieve high energy efficiency by
processing the data within the memory, which makes it well-suited for applications like …
processing the data within the memory, which makes it well-suited for applications like …
Evaluating the impact of process variation on RRAMs
E Brum, M Fieback, TS Copetti, H Jiayi… - 2021 IEEE 22nd …, 2021 - ieeexplore.ieee.org
Over the last fifty years Complementary Metal Oxide Semiconductor (CMOS) technology has
been scaled down, making the design of high-performance applications possible. However …
been scaled down, making the design of high-performance applications possible. However …
Mitigating the effects of RRAM process variation on the accuracy of artificial neural networks
M Fritscher, J Knödtel, M Mallah, S Pechmann… - … on Embedded Computer …, 2021 - Springer
Weight storage is a key challenge in the efficient implementation of artificial neural networks.
Novel memory technologies such as RRAM are able to greatly improve density and …
Novel memory technologies such as RRAM are able to greatly improve density and …
Digital offset for rram-based neuromorphic computing: A novel solution to conquer cycle-to-cycle variation
Resistance variation in memristor device hinders the practical use of resistive random
access memory (RRAM) crossbars as neural network (NN) accelerators. Previous fault …
access memory (RRAM) crossbars as neural network (NN) accelerators. Previous fault …
An Empirical Fault Vulnerability Exploration of ReRAM-Based Process-in-Memory CNN Accelerators
A Dorostkar, H Farbeh… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Resistive random-access memory (ReRAM)-based processing-in-memory (PIM) accelerator
is a promising platform for processing massively memory intensive matrix-vector …
is a promising platform for processing massively memory intensive matrix-vector …
A Hardware Friendly Variation-Tolerant Framework for RRAM-Based Neuromorphic Computing
FY Gu, CH Yang, C Lin, DW Chang… - … on Circuits and …, 2024 - ieeexplore.ieee.org
Emerging resistive random access memory (RRAM) attracts considerable interest in
computing-in-memory by its high efficiency in multiply-accumulate operation, which is the …
computing-in-memory by its high efficiency in multiply-accumulate operation, which is the …