Ghent University Academic Bibliography

Show Sort by

Your filters: cql: affiliation exact TW cql: author exact 801000802531

Add to list
- Journal Article
- open access
Iterative neural networks for adaptive inference on resource-constrained devices

Sam Leroux (UGent) , Tim Verbelen (UGent) , Pieter Simoens (UGent) and Bart Dhoedt (UGent)

(2022) NEURAL COMPUTING & APPLICATIONS. p.1-16
Add to list
- Journal Article
- A1
- open access
Leveraging the Bhattacharyya coefficient for uncertainty quantification in deep neural networks

Pieter Van Molle (UGent) , Tim Verbelen (UGent) , Bert Vankeirsbilck (UGent) , Jonas De Vylder (UGent) , Bart Diricx, Tom Kimpe, Pieter Simoens (UGent) and Bart Dhoedt (UGent)

(2021) NEURAL COMPUTING & APPLICATIONS. 33(16). p.10259-10275
Add to list
Robot navigation as hierarchical active inference

Ozan Catal (UGent) , Tim Verbelen (UGent) , Toon Van de Maele (UGent) , Bart Dhoedt (UGent) and Adam Safron

(2021) NEURAL NETWORKS. 142. p.192-204
Add to list
- Conference Paper
- C1
- open access
Towards bio-inspired unsupervised representation learning for indoor aerial navigation

Ni Wang (UGent) , Ozan Catal (UGent) , Tim Verbelen (UGent) , Matthias Hartmann and Bart Dhoedt (UGent)

(2021) ICRA2021, the IEEE International Conference on Robotics and Automation, Workshops, Proceedings.
Add to list
- Conference Paper
- C1
- open access
Self-supervised exploration via latent Bayesian surprise

Pietro Mazzaglia (UGent) , Ozan Catal (UGent) , Tim Verbelen (UGent) and Bart Dhoedt (UGent)

(2021) ICLR 2021, Self-supervision for Reinforcement Learning, Proceedings.
Add to list
- Journal Article
- A1
- open access
Active vision for robot manipulators using the free energy principle

Toon Van de Maele (UGent) , Tim Verbelen (UGent) , Ozan Catal (UGent) , Cedric De Boom (UGent) and Bart Dhoedt (UGent)

(2021) FRONTIERS IN NEUROROBOTICS. 15.
Add to list
- Conference Paper
- P1
- open access
Disentangling what and where for 3D object-centric representations through active inference

Toon Van de Maele (UGent) , Tim Verbelen (UGent) , Ozan Catal (UGent) and Bart Dhoedt (UGent)

(2021) MACHINE LEARNING AND PRINCIPLES AND PRACTICE OF KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2021, PT I. In Communications in Computer and Information Science 1524. p.701-714
Add to list
- Conference Paper
- C1
- open access
A learning gap between neuroscience and reinforcement learning

Samuel Wauthier (UGent) , Pietro Mazzaglia (UGent) , Ozan Catal (UGent) , Cedric De Boom (UGent) , Tim Verbelen (UGent) and Bart Dhoedt (UGent)

(2021) BRAIN2AI, How Can Findings About The Brain Improve AI Systems, ICLR 2021 Workshop, Proceedings.
Add to list
- Conference Paper
- P1
- open access
Dynamic narrowing of VAE bottlenecks using GECO and L0 regularization

Cedric De Boom (UGent) , Samuel Wauthier (UGent) , Tim Verbelen (UGent) and Bart Dhoedt (UGent)

(2021) 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN). In IEEE International Joint Conference on Neural Networks (IJCNN)
Add to list
LatentSLAM : unsupervised multi-sensor representation learning for localization and mapping

Ozan Catal (UGent) , Wouter Jansen, Tim Verbelen (UGent) , Bart Dhoedt (UGent) and Jan Steckel

(2021) 2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021). In IEEE International Conference on Robotics and Automation ICRA p.6739-6745

Academic Bibliography

Iterative neural networks for adaptive inference on resource-constrained devices

Leveraging the Bhattacharyya coefficient for uncertainty quantification in deep neural networks

Robot navigation as hierarchical active inference

Towards bio-inspired unsupervised representation learning for indoor aerial navigation

Self-supervised exploration via latent Bayesian surprise

Active vision for robot manipulators using the free energy principle

Disentangling what and where for 3D object-centric representations through active inference

A learning gap between neuroscience and reinforcement learning

Dynamic narrowing of VAE bottlenecks using GECO and L0 regularization

LatentSLAM : unsupervised multi-sensor representation learning for localization and mapping

Contents

Support

Contact