04b Atto di convegno in volume | Department of Computer, Control and Management Engineering

04b Atto di convegno in volume

Investigating Graph Embedding Neural Networks with Unsupervised Features Extraction for Binary Analysis

In this paper we investigate the use of graph embedding networks, with unsupervised features learning, as neural architecture to learn over binary functions. We propose several ways of automatically extract features from the control ﬂow graph (CFG) and we use the structure2vec graph embedding...
Single-trial Connectivity Estimation through the Least Absolute Shrinkage and Selection Operator
Estimation of brain connectivity through Artificial Neural Networks
Electroencephalography (EEG)-Derived Markers to Measure Components of Attention Processing
Interfacing brain and computer in neurorehabilitation
Frontal EEG theta changes assess the training improvements of novices in flight simulation tasks
Robust Real-Time Whole-Body Motion Retargeting from Human to Humanoid

Transferring the motion from a human operator to a humanoid robot is a crucial step to enable robots to learn from and replicate human movements. The ability to retarget in realtime whole-body motions that are challenging for the humanoid balance is critical to enable human to humanoid...
Hi-Val: Iterative Learning of Hierarchical Value Functions for Policy Generation
Q-CP: Learning Action Values for Cooperative Planning
DOP: Deep Optimistic Planning with Approximate Value Function Evaluation

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma