217 citations · 409 across the 17 of their papers we have counts for
7 papers · 1 filter
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…
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…
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…
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…
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…