Projektbeschreibung
Die Komplexität des Deep Learnings entwirren
Tiefe neuronale Netzwerke haben sich in fast allen Branchen durchgesetzt und bilden die vorderste Front der künstlichen Intelligenz (KI). Ungeachtet ihrer hohen Leistung weisen tiefe neuronale Netzwerke Schwächen auf. Für Menschen sind die komplexen Modelle schwer zu interpretieren und zu analysieren. Auch tiefe neuronale Netzwerke leiden unter Verzerrungseffekten. Das EU-finanzierte Projekt RRR-XAI wird diese Mängel beheben, indem es für eine bessere Verständlichkeit des Deep Learnings sorgt. Es wird Analysen durchführen, um sich der verschiedenen Arten von Phänomenen bewusst zu werden, die bei tiefen neuronalen Netzwerken Probleme bereiten. Zu diesem Zweck werden Fallstudien durchgeführt, die sich mit der COVID-19-Vorhersage anhand von Röntgenbildern des Brustkorbs, der Waffenerkennung in Alarmsystemen und der Erkennung von Menschenmengen auf Bildmaterial beschäftigen.
Ziel
Deep Learning (DL) is a form of machine learning (ML) that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. This hierarchy allows a DL model to learn complicated concepts by building them out of simpler ones. A graph of these hierarchies would be many layers deep, and thus its name. A Deep neural network (DNN) is based on an artificial neural network model, and its core strength is that there is no need for human assistance to formally specify all the knowledge that the model needs. This makes DNNs represent the state of the art in Artificial Intelligence (AI). Despite their top performance and ubiquity of applications (from Healthcare to autonomous cars), DNNs suffer serious shortcomings. First, DNNs are considered black box models, i.e. with complex and opaque algorithms, hard to interpret and diagnose. Second, they suffer from bias, and the testing protocols for automatic recognition are not fair, as they learn patterns in the data that are not correlated to the output; e.g. they may focus on areas outside the lung in X ray images to predict the presence of COVID-19. Although DNNs outperform many other methods, they often are not right for the right reasons (RRR). RRR-XAI tackles this mismatch and bridges this gap through a tight integration of DL and symbolic AI, with the principal objective of making DL explainable. To achieve this I will follow the rationale behind XAI under the RRR philosophy and perform analyses to understand two types of phenomena that cause trouble in DNNs. Second, I will use: 1) Domain knowledge expertise as supporting evidence to explain a particular model output; 2) Neural-Symbolic computation to communicate the explanation of such phenomena in natural language. I will study two practical use cases where supporting explanations of the model output are critical: a) COVID-19 prediction from chest X-Ray images, and b) Weapon detection in alarm systems and crowds from images.
Wissenschaftliches Gebiet
- 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
Schlüsselbegriffe
Programm/Programme
- HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) Main Programme
Aufforderung zur Vorschlagseinreichung
Andere Projekte für diesen Aufruf anzeigenFinanzierungsplan
HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European FellowshipsKoordinator
18071 Granada
Spanien