217 citations · 409 across the 17 of their papers we have counts for
3 papers · 1 filter
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…
CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks
Alberto Marchisio, Giorgio Nanfa, Faiq Khalid +3
Capsule Networks preserve the hierarchical spatial relationships between objects, and thereby bears a potential to surpass the performance of traditional Convolutional Neural Netwo…