Interpretation and Explanation of Deep Computer Vision
Praktische info:
Inschrijven?
- Inschrijvingen: tot 17 jan. 2023
- Prijs: Free
Do you need a certificate of attendance to this course? Send us an email and we will take care of it.
Participation is free but registration is mandatory. Please register in order to receive the link to the course. This will be sent the day before the seminar 👇
georganiseerd door:
Leertrajecten
In 2012, AlexNet [Krizhevsky et al., NeurIPS'12] shook the field with the remarkable performance it obtained on the task of image recognition at a large scale. This showed the potential of artificial neural networks, and deep models in general, for modeling visual data. At the same time, this motivated the adoption of deep models by both academia and industry to the point of making these models the standard when building AI systems for visual data.
Despite their high predictive performance, follow up work showed that the complex structure that characterize these models obscures what characteristics or features of the training data are internally encoded in the model (Interpretation). At the same time, it is hard to assess what characteristics from a given input are considered by the model when making a prediction for such input.
In this course we will discuss relevant methods that have been proposed to address these two tasks, introduce some evaluation protocols and set some perspectives towards current and future directions.
Lesgever/spreker
José Oramas
José Oramas is an Assistant Professor at the Internet Data Lab (IDLab) a joint research lab between the University of Antwerp and IMEC. He received his PhD at the Center for Processing Speech and Images (ESAT-PSI) of KU Leuven in April 2015. Earlier he received his engineering degree from Escuela Superior Politecnica del Litoral in Ecuador. During his Ph.D. he conducted research on understanding how groups of elements from the image (objects, object-parts, image regions, trajectories, etc.) interact and how the relationships between them can be exploited to improve artificial visual perception problems. This fueled his interest towards investigating exploratory/explanatory models that can identify informative intermediate representations and use them as means to justify the predictions that they make.
Research Interests: Representation Learning, Interpretability and Explainability, Multiple Instance Learning, Machine Learning, Deep Learning and Computer Vision
VAIA and Trail Joint Seminar Series for researchers
In this seminar series, we bring together researchers that are interested in, or conducting research on AI and Machine Learning. Each VAIA-TRAIL doctoral course focuses on a specific topic ranging from times series to reinforcement learning to combat epidemics and interpretable & explainable Deep Learning.
Gerelateerde opleidingen
