217 citations · 803 across the 83 of their papers we have counts for
25 papers · 1 filter
Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models
Muhammad Shafique, Abdul Basit, Muhammad Abdullah Hanif +3
This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-design of transformer blocks w…
How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations
Nouhaila Innan, Antonello Rosato, Alberto Marchisio +1
Node embeddings act as the information interface for graph neural networks, yet their empirical impact is often reported under mismatched backbones, splits, and training budgets. T…
Design Space Exploration of Hybrid Quantum Neural Networks for Chronic Kidney Disease
Muhammad Kashif, Hanzalah Mohamed Siraj, Nouhaila Innan +2
Hybrid Quantum Neural Networks (HQNNs) have recently emerged as a promising paradigm for near-term quantum machine learning. However, their practical performance strongly depends o…
FAQNAS: FLOPs-aware Hybrid Quantum Neural Architecture Search using Genetic Algorithm
Muhammad Kashif, Shaf Khalid, Alberto Marchisio +2
Hybrid Quantum Neural Networks (HQNNs), which combine parameterized quantum circuits with classical neural layers, are emerging as promising models in the noisy intermediate-scale…
Neuromorphic Computing for Embodied Intelligence in Autonomous Systems: Current Trends, Challenges, and Future Directions
Alberto Marchisio, Muhammad Shafique
The growing need for intelligent, adaptive, and energy-efficient autonomous systems across fields such as robotics, mobile agents (e.g., UAVs), and self-driving vehicles is driving…
QFAL: Quantum Federated Adversarial Learning
Walid El Maouaki, Nouhaila Innan, Alberto Marchisio +3
Quantum federated learning (QFL) merges the privacy advantages of federated systems with the computational potential of quantum neural networks (QNNs), yet its vulnerability to adv…
MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks
Lotfi Abdelkrim Mecharbat, Alberto Marchisio, Muhammad Shafique +2
There has been a surge in optimizing edge Deep Neural Networks (DNNs) for accuracy and efficiency using traditional optimization techniques such as pruning, and more recently, empl…
TinyCL: An Efficient Hardware Architecture for Continual Learning on Autonomous Systems
Eugenio Ressa, Alberto Marchisio, Maurizio Martina +2
The Continuous Learning (CL) paradigm consists of continuously evolving the parameters of the Deep Neural Network (DNN) model to progressively learn to perform new tasks without re…
SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers
Alberto Marchisio, Davide Dura, Maurizio Capra +3
Transformers' compute-intensive operations pose enormous challenges for their deployment in resource-constrained EdgeAI / tinyML devices. As an established neural network compressi…
RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks
Alberto Marchisio, Antonio De Marco, Alessio Colucci +2
Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships between multiple objects for image classification tasks. Other than achieving high accuracy,…
AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient
Farzad Nikfam, Alberto Marchisio, Maurizio Martina +1
Adversarial training is exploited to develop a robust Deep Neural Network (DNN) model against the malicious altered data. These attacks may have catastrophic effects on DNN models…
RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks
Alberto Marchisio, Vojtech Mrazek, Andrea Massa +3
Neural Architecture Search (NAS) algorithms aim at finding efficient Deep Neural Network (DNN) architectures for a given application under given system constraints. DNNs are comput…
Enabling Capsule Networks at the Edge through Approximate Softmax and Squash Operations
Alberto Marchisio, Beatrice Bussolino, Edoardo Salvati +3
Complex Deep Neural Networks such as Capsule Networks (CapsNets) exhibit high learning capabilities at the cost of compute-intensive operations. To enable their deployment on edge…
fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systems
Alberto Marchisio, Giovanni Caramia, Maurizio Martina +1
Recently, Deep Neural Networks (DNNs) have achieved remarkable performances in many applications, while several studies have enhanced their vulnerabilities to malicious attacks. In…
R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors
Alberto Marchisio, Giacomo Pira, Maurizio Martina +2
Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS). This pa…
MLComp: A Methodology for Machine Learning-based Performance Estimation and Adaptive Selection of Pareto-Optimal Compiler Optimization Sequences
Alessio Colucci, Dávid Juhász, Martin Mosbeck +6
Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjec…
Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
Rida El-Allami, Alberto Marchisio, Muhammad Shafique +1
Deep Learning (DL) algorithms have gained popularity owing to their practical problem-solving capacity. However, they suffer from a serious integrity threat, i.e., their vulnerabil…
DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware
Alberto Marchisio, Vojtech Mrazek, Muhammad Abdullah Hanif +1
Deep Neural Networks (DNNs) have been established as the state-of-the-art algorithm for advanced machine learning applications. Recently proposed by the Google Brain's team, the Ca…
NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks
Alberto Marchisio, Andrea Massa, Vojtech Mrazek +3
Deep Neural Networks (DNNs) have made significant improvements to reach the desired accuracy to be employed in a wide variety of Machine Learning (ML) applications. Recently the Go…
Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks
Alberto Marchisio, Beatrice Bussolino, Alessio Colucci +3
Capsule Networks (CapsNets), recently proposed by the Google Brain team, have superior learning capabilities in machine learning tasks, like image classification, compared to the t…
ReD-CaNe: A Systematic Methodology for Resilience Analysis and Design of Capsule Networks under Approximations
Alberto Marchisio, Vojtech Mrazek, Muhammad Abudllah Hanif +1
Recent advances in Capsule Networks (CapsNets) have shown their superior learning capability, compared to the traditional Convolutional Neural Networks (CNNs). However, the extreme…
FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule Networks
Alberto Marchisio, Beatrice Bussolino, Alessio Colucci +4
Recently, Capsule Networks (CapsNets) have shown improved performance compared to the traditional Convolutional Neural Networks (CNNs), by encoding and preserving spatial relations…
CapStore: Energy-Efficient Design and Management of the On-Chip Memory for CapsuleNet Inference Accelerators
Alberto Marchisio, Muhammad Abdullah Hanif, Mohammad Taghi Teimoori +1
Deep Neural Networks (DNNs) have been established as the state-of-the-art algorithm for advanced machine learning applications. Recently, CapsuleNets have improved the generalizati…
Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks
Alberto Marchisio, Giorgio Nanfa, Faiq Khalid +3
Spiking Neural Networks (SNNs) claim to present many advantages in terms of biological plausibility and energy efficiency compared to standard Deep Neural Networks (DNNs). Recent w…