Recurrent neural network pruning using dynamical systems and iterative fine-tuning
Christos Chatzikonstantinou, Dimitrios Konstantinidis, Kosmas Dimitropoulos and Petros Daras. Network pruning techniques are widely employed to reduce the memory requirements and increase the inference speed of neural networks. This work proposes a novel RNN pruning method that considers the...
Read MoreNAct: The Nutrition and Activity Ontology
D. Tsatsou, Elena Lalama, S. L. Wilson-Barnes, K. Hart, V. Cornelissen, R. Buys, I. Pagkalos, S. Balula Dias, K. Dimitropoulos, P. Daras. NAct: The Nutrition & Activity Ontology for healthy living. Formal Ontology in Information Systems: Proceedings of the 12th...
Read MorePersonalised nutrition for healthy living: The PROTEIN project
S. Wilson-Barnes, L. P. Gymnopoulos, K. Dimitropoulos, V. Solachidis, K. Rouskas, D. Russell, Y. Oikonomidis, S. Hadjidimitriou, J. María Botana, B. Brkic, E. Mantovani, S. Gravina, G. Telo, E. Lalama, R. Buys, M. Hassapidou, S. Balula Dias, A. Batista, L....
Read MoreNoise-Assisted Multivariate variational mode decomposition
Charilaos A. Zisou, Georgios K. Apostolidis, Leontios J. Hadjileontiadis The variational mode decomposition (VMD) is a widely applied optimization-based method, which analyzes nonstationary signals concurrently. Correspondingly, its recently proposed multivariate extension, i.e., MVMD, has shown great potentials in analyzing multichannel...
Read MoreA Deep Network for Automatic Video-Based Food Bite Detection
Dimitrios Konstantinidis, Kosmas Dimitropoulos, Ioannis Ioakimidis, Billy Lang-Le, Petros Daras Past research has now provided compelling evidence pointing towards correlations among individual eating styles and the development of (un)healthy eating patterns, obesity and other medical conditions. In this setting, an...
Read More