VIRTUEL - Reconeixement visual emprant metodologies d'aprenentatge de principi a fi: teoria i aplicacions
Area: Technology and communication
PI: Lapedriza García, Ágata; Masip Rodó, David
Research group: SUNAI - Scene understanding and artificial intelligence lab
Project status: Open
Funding institution: Ministerio de Economía y Competitividad - España
Dates: 2016-2018
Objectives: This project proposes to design new learning algorithms used in computer vision to improve some of the open issues in this field. The project will focus on: The use of the large volume of unlabelled data available to improve the performance of learning algorithms, designing end-to-end learning architectures that model temporal and sequential dynamics in data, and the use of sparse representations in learning parameters to significantly reduce the training time of deep CNNs.