Project description
Untangling the complexity of deep learning
Having penetrated nearly all industries, deep neural networks (DNNs) are at the cutting edge of AI. Despite the high level of performance, DNNs have flaws. Humans find the complex models hard to interpret and analyse. DNNs also suffer from bias. The EU-funded RRR-XAI project aims to tackle these shortcomings by making deep learning understandable. It will carry out analyses to become aware of the different kinds of phenomena that create problems for DNNs. To do so, it will conduct case studies involving COVID-19 prediction from chest X-ray images and weapon detection in alarm systems and crowds from images.
Fields of science
- engineering and technologymechanical engineeringvehicle engineeringautomotive engineeringautonomous vehicles
- medical and health scienceshealth sciencesinfectious diseasesRNA virusescoronaviruses
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
- humanitiesphilosophy, ethics and religionphilosophy
Keywords
Programme(s)
- HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) Main Programme
Funding Scheme
HORIZON-AG-UN - HORIZON Unit Grant
Coordinator
UNIVERSIDAD DE GRANADA
Net EU contribution
€ 165 312,96
Address
Cuesta Del Hospicio Sn
18071 Granada
Spain
18071 Granada
Spain
See on map
Region
Andalucía Granada
Activity type
Higher or Secondary Education Establishments
Other funding
No data
Partners (1)
UNIVERSITA DEGLI STUDI DI SIENA
Italy
Net EU contribution
€ 0,00
Address
Via Banchi Di Sotto 55
53100 Siena
53100 Siena
See on map
Region
Centro (IT) Toscana Siena
Activity type
Higher or Secondary Education Establishments
Other funding
No data