In this paper, we present a comprehensive survey of the current trends
f...
In this paper, we investigate the vulnerability of MDE to adversarial
pa...
The challenging deployment of compute-intensive applications from domain...
The rapid growth of demanding applications in domains applying multimedi...
Fault-aware retraining has emerged as a prominent technique for mitigati...
Permanent faults induced due to imperfections in the manufacturing proce...
In this paper, we present a novel approach for generating naturalistic
a...
Fault-Aware Training (FAT) has emerged as a highly effective technique f...
To maximize the performance and energy efficiency of Spiking Neural Netw...
Spiking Neural Networks (SNNs) have shown capabilities of achieving high...
Graph neural networks (GNNs) have shown great success in detecting
intel...
Approximate computing (AC) has become a prominent solution to improve th...
Machine Learning (ML) architectures have been applied to several applica...
In recent years, monocular depth estimation (MDE) has witnessed a substa...
Vision-based perception modules are increasingly deployed in many
applic...
In today's era of smart cyber-physical systems, Deep Neural Networks (DN...
The real-world use cases of Machine Learning (ML) have exploded over the...
Specialized hardware accelerators have been designed and employed to max...
Logic locking aims to prevent intellectual property (IP) piracy and
unau...
The security and privacy concerns along with the amount of data that is
...
Spiking neural networks (SNNs) have shown a potential for having low ene...
Approximate computing is an emerging paradigm to improve power and
perfo...
Continual learning is essential for all real-world applications, as froz...
From tiny pacemaker chips to aircraft collision avoidance systems, the
s...
Spiking Neural Networks (SNNs) have the potential for achieving low ener...
Negative Biased Temperature Instability (NBTI)-induced aging is one of t...
In this paper, we propose GNNUnlock, the first-of-its-kind oracle-less
m...
Deep Neural Networks (DNNs) have been established as the state-of-the-ar...
Many convolutional neural network (CNN) accelerators face performance- a...
With a constant improvement in the network architectures and training
me...
Deep Neural Networks (DNNs) are widely being adopted for safety-critical...
The state-of-the-art approaches employ approximate computing to improve ...
Convolutional Neural Networks (CNNs) are extensively in use due to their...
Approximate computing is an emerging paradigm for developing highly
ener...
Many hardware accelerators have been proposed to improve the computation...
Recently, many adversarial examples have emerged for Deep Neural Network...
Due to data dependency and model leakage properties, Deep Neural Network...
Capsule Networks envision an innovative point of view about the
represen...
The exponential increase in dependencies between the cyber and physical ...
Recent studies have shown that slight perturbations in the input data ca...
Deep Neural Networks (DNNs) have recently been shown vulnerable to
adver...
Due to big data analysis ability, machine learning (ML) algorithms are
b...
Deep Neural Networks (DNNs) have been widely deployed for many Machine
L...
The state-of-the-art accelerators for Convolutional Neural Networks (CNN...
Activation functions influence behavior and performance of DNNs. Nonline...