Litcius/Paper detail

NASCaps

Alberto Marchisio, Andrea Massa, Vojtech Mrazek, Beatrice Bussolino, Maurizio Martina, Muhammad Shafique

202039 citationsDOIOpen Access PDF

Abstract

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 Google Brain's team demonstrated the ability of Capsule Networks (CapsNets) to encode and learn spatial correlations between different input features, thereby obtaining superior learning capabilities compared to traditional (i.e., non-capsule based) DNNs. However, designing CapsNets using conventional methods is a tedious job and incurs significant training effort. Recent studies have shown that powerful methods to automatically select the best/optimal DNN model configuration for a given set of applications and a training dataset are based on the Neural Architecture Search (NAS) algorithms. Moreover, due to their extreme computational and memory requirements, DNNs are employed using the specialized hardware accelerators in IoT-Edge/CPS devices.

Topics & Concepts

Computer scienceArtificial intelligenceArtificial neural networkSet (abstract data type)Variety (cybernetics)ENCODETraining setMachine learningDeep learningDeep neural networksFeature (linguistics)ArchitectureKey (lock)Feature extractionData setAdvanced Neural Network ApplicationsAdversarial Robustness in Machine LearningMachine Learning and ELM
NASCaps | Litcius