Researcher

José Antonio Oramas Mogrovejo

Research Expertise (University of Antwerp):Research interest: - Visual Representation Learning. - Model Explanation and Interpretation. - Collective Representations and Relational Learning. - Disentangled Representation Learning.

Keywords (University of Antwerp):INTERPRETABLE ARTIFICIAL INTELLIGENCE, EXPLAINABLE ARTIFICIAL INTELLIGENCE, MACHINE LEARNING, COMPUTER VISION, REPRESENTATION LEARNING, ARTIFICIAL INTELLIGENCE (AI), Computer science (incl. applied informatics)

Disciplines (Interuniversity Microelectronics Centre):Display technology, Antennas and propagation, Automation and control systems, Analogue, RF and mixed signal integrated circuits, Neuromorphic computing, Audio and speech processing, Environmental safety and health of nanotechnology, Battery technology, Biomaterials, Ceramic matrix composites, Hybrid composites, Computational materials science, Metals and alloy materials, Polymer processing, Nanomaterials, Functional materials, Biomedical image processing, Biochemical engineering, Biofluid mechanics, Cell, tissue and organ engineering, Arithmetic and logic structures, Automation, feedback control and robotics, Bio-informatics, Analogue and digital signal processing, Engineering instrumentation, Environmental health and safety, Biostatistics, Care for disabled, Bioethics
Disciplines (University of Antwerp):Knowledge representation and reasoning, Machine learning and decision making, Artificial intelligence not elsewhere classified, Computer vision, Pattern recognition and neural networks
Disciplines (KU Leuven):Artificial intelligence, Multimedia processing, Biological system engineering, Signal processing, Other computer engineering, information technology and mathematical engineering, Medical imaging and therapy

Research techniques (University of Antwerp):- Computer Vision - Machine Learning - Artificial Intelligence

Users of research expertise (University of Antwerp):Any individual or company with an AI-based system implemented through deep neural networks that needs to: - Verify the type of features encoded internally in the representation learned by the network. - Verify potential biases present in the internal representation of the network. - Justify the predictions made by the network. . Any individual or company - Obtaining an insight on patterns found in large collections of images. - Perform recognition and detection tasks from visual data (videos and images).