Bart Dhoedt

Bart Dhoedt

Bart Dhoedt

email: Bart.Dhoedt@UGent.be
tel.: +32 9 331 49 21
research group: IDLab
team

Bart Dhoedt received a Masters degree in Electro-technical Engineering (1990) from Ghent University. His research, addressing the use of micro-optics to realize parallel free space optical interconnects, resulted in a Ph.D. degree in 1995. After a 2-year post-doc in opto-electronics, he became Professor at the Department of Information Technology.

Bart Dhoedt is responsible for various courses on algorithms, advanced programming, software development and distributed systems. His research interests include distributed machine learning, edge computing and hardware friendly machine learning. He is author or co-author of more than 300 publications in international journals or conference proceedings.

Keywords: Distributed Machine Learning, Sensor Fusion, Representation Learning, Edge Computing, Neuromorphic Computing

Key publications

  • DIANNE: a modular framework for designing, training and deploying deep neural networks on heterogeneous distributed infrastructure By: De Coninck, Elias; Bohez, Steven; Leroux, Sam; et al. JOURNAL OF SYSTEMS AND SOFTWARE Volume: 141 Pages: 52-65 Published: JUL 2018 (citations : 0, recent publication)

  • The cascading neural network: building the Internet of Smart Things By: Leroux, Sam; Bohez, Steven; De Coninck, Elias; et al. KNOWLEDGE AND INFORMATION SYSTEMS Volume: 52 Issue: 3 Pages: 791-814 Published: SEP 2017 (citations : 6)

  • Sensor Fusion for Robot Control through Deep Reinforcement Learning By: Bohez, Steven; Verbelen, Tim; De Coninck, Elias; et al. Conference: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Location: Vancouver, CANADA Date: SEP 24-28, 2017 Sponsor(s): IEEE; RSJ; IEEE Robot & Automat Soc; IEEE IES; SICE; New Technol Fdn 2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) Book Series: IEEE International Conference on Intelligent Robots and Systems Pages: 2365-2370 Published: 2017 (citations : 5)

  • Representation learning for very short texts using weighted word embedding aggregation By: De Boom, Cedric; Van Canneyt, Steven; Demeester, Thomas; et al. PATTERN RECOGNITION LETTERS Volume: 80 Pages: 150-156 Published: SEP 1 2016 (citations : 35)

  • Georeferencing Flickr resources based on textual meta-data By: Van Laere, Olivier; Schockaert, Steven; Dhoedt, Bart INFORMATION SCIENCES Volume: 238 Pages: 52-74 Published: JUL 20 2013, (citations: 34)

Publication links