Respawn: Energy-efficient fault-tolerance for spiking neural networks considering unreliable memories
Spiking neural networks (SNNs) have shown a potential for having low energy with
unsupervised learning capabilities due to their biologically-inspired computation. However …
unsupervised learning capabilities due to their biologically-inspired computation. However …
Sparkxd: A framework for resilient and energy-efficient spiking neural network inference using approximate dram
Spiking Neural Networks (SNNs) have the potential for achieving low energy consumption
due to their biologically sparse computation. Several studies have shown that the off-chip …
due to their biologically sparse computation. Several studies have shown that the off-chip …
Spiking neuron hardware-level fault modeling
SA El-Sayed, T Spyrou, A Pavlidis… - 2020 IEEE 26th …, 2020 - ieeexplore.ieee.org
The deployment of Artificial Intelligence (AI) hardware accelerators in a variety of
applications, including safety-critical ones, requires assessing their inherent reliability to …
applications, including safety-critical ones, requires assessing their inherent reliability to …
Spikedyn: A framework for energy-efficient spiking neural networks with continual and unsupervised learning capabilities in dynamic environments
RVW Putra, M Shafique - 2021 58th ACM/IEEE Design …, 2021 - ieeexplore.ieee.org
Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual
learning capabilities because of their biological plausibility, but their complexity still poses a …
learning capabilities because of their biological plausibility, but their complexity still poses a …
EnforceSNN: Enabling resilient and energy-efficient spiking neural network inference considering approximate DRAMs for embedded systems
Spiking Neural Networks (SNNs) have shown capabilities of achieving high accuracy under
unsupervised settings and low operational power/energy due to their bio-plausible …
unsupervised settings and low operational power/energy due to their bio-plausible …
Binarized snns: Efficient and error-resilient spiking neural networks through binarization
Spiking Neural Networks (SNNs) are considered the third generation of NNs and can reach
similar accuracy as conventional deep NNs, but with a considerable improvement in …
similar accuracy as conventional deep NNs, but with a considerable improvement in …
Neuron fault tolerance in spiking neural networks
The error-resiliency of Artificial Intelligence (AI) hardware accelerators is a major concern,
especially when they are deployed in mission-critical and safety-critical applications. In this …
especially when they are deployed in mission-critical and safety-critical applications. In this …
Fspinn: An optimization framework for memory-efficient and energy-efficient spiking neural networks
RVW Putra, M Shafique - IEEE Transactions on Computer …, 2020 - ieeexplore.ieee.org
Spiking neural networks (SNNs) are gaining interest due to their event-driven processing
which potentially consumes low-power/energy computations in hardware platforms while …
which potentially consumes low-power/energy computations in hardware platforms while …
SoftSNN: Low-cost fault tolerance for spiking neural network accelerators under soft errors
Specialized hardware accelerators have been designed and employed to maximize the
performance efficiency of Spiking Neural Networks (SNNs). However, such accelerators are …
performance efficiency of Spiking Neural Networks (SNNs). However, such accelerators are …
Improving reliability of spiking neural networks through fault aware threshold voltage optimization
A Siddique, KA Hoque - 2023 Design, Automation & Test in …, 2023 - ieeexplore.ieee.org
Spiking neural networks have made breakthroughs in computer vision by lending
themselves to neuromorphic hardware. However, the neuromorphic hardware lacks …
themselves to neuromorphic hardware. However, the neuromorphic hardware lacks …