“Signal Processing in the AI era” was the tagline of this year’s IEEE International Conference on Acoustics, Speech and Signal Processing, taking place in Rhodes, Greece.
In this context, Brent de Weerdt, Xiangyu Yang, Boris Joukovsky, Alex Stergiou and Nikos Deligiannis presented ETRO’s research during poster sessions and oral presentations, with novel ways to process and understand graph, video, and audio data. Nikos Deligiannis chaired a session on Graph Deep Learning, attended the IEEE T-IP Editorial Board Meeting, and had the opportunity to meet with collaborators from the VUB-Duke-Ugent-UCL joint lab.
Featured articles:
- De Weerdt, B. et al., “Designing Transformer Networks for Sparse Recovery of Sequential Data Using Deep Unfolding” (https://ieeexplore.ieee.org/abstract/document/10094712)
- Yang X. et al., “Relevance Propagation through Deep Conditional Random Fields” (https://ieeexplore.ieee.org/abstract/document/10095075)
- Stergiou A. et al., “Play it back: Iterative attention for audio recognition” (https://ieeexplore.ieee.org/abstract/document/10096532, developed at the University of Bristol)
ETRO gave a presentation on 16 June about the TRM radar technology “to look into the walls” on the FLANDERS INTERNATIONAL DAY of SMART HUB VLAAMS-BRABANT to the international representatives of the Flanders Trade and Invest (FIT) aka the key point of contact for international business in Flanders, but also for export of Flemish business to abroad.
Today the results of Fonds Wetenschappelijk Onderzoek – Vlaanderen Mandaten aspirant strategisch basisonderzoek were announced. 196 Mandates were awarded, 13 for VUB and TWO for ETRO. Very well done, Cedric Baijot (prom. Maarten Kuijk) and Salar Tayebi (Prom. Johan Stiens)! Also Delphine Van Laethem, who is doing a PhD with Jeroen Van Schependom will get the scholarship.
ETRO was highly visible and omni-present at the HealthTech Brussels event hosted by FARI, showcasing cutting-edge AI expertise in health. We hope the networking opportunities helped create valuable new connections with the entrepreneurs and clinicians who attended.
On March 12 2021 at 16.00 Evgenia Papavasileiou will defend her PhD entitled “Towards more Efficient NeuroEvolution: Application on Feature Selection and Classification Problems”.
NeuroEvolution (NE) is a sub-field of Artificial Intelligence whose purpose is to optimize Artificial Neural Networks (ANNs) by modeling the biological evolutionary process. NeuroEvolution of Augmenting Topologies (NEAT) that evolves the topology and the connectivity weights of the ANNs, is one of the most influential algorithms in the field. This PhD performs different studies on NEAT extensions, namely FD-NEAT, FS-NEAT and HA-NEAT and proposes new extensions so that the resulting methods could require fewer generations, evolve smaller and less complex networks and scale on complex problems.
After the publication of NEAT in 2002 many methods have appeared that extend its functionality in various ways. In this PhD, a systematic review is performed to identify and categorize the NEAT’s successors. The proposed clustering scheme can support researchers 1) understanding the current state of the art that will enable them 2) exploring new research directions or 3) benchmarking their proposed method to the state of the art, if they are interested in comparing, and 4) positioning themselves in the domain or 5) selecting a method that is most appropriate for their problem. In addition, different studies are conducted to achieve important intermediate stepping stones. The first set of investigations concern design choices in the initial topologies of two NEAT extensions, namely FD-NEAT and FS-NEAT. These include the introduction of a hidden layer in the initial topologies, the initialization of the topologies with a different connectivity setting and the employment of different activation functions in the output layer. Additionally, BS-HA-NEAT and BS-NEAT are proposed as new extensions of HA-NEAT and NEAT, that perform speciation in the behavioral rather than in the genotypic space. It is found that BS-HA-NEAT and BS-NEAT outperform HA-NEAT and NEAT solving previously unsolvable problems or improving the accuracy and reducing the complexity of the evolved networks. Furthermore, HA-FD-NEAT, extending both HA-NEAT and FD-NEAT is proposed. This is able to evolve the topology, the connectivity weights and the activation functions of ANNs while identifying the relevant features. HA-FD-NEAT outperforms HA-NEAT and performs as good as FD-NEAT. Also, BS-HA-FD-NEAT is proposed as an extension to HA-FD-NEAT by performing speciation in the behavioral space. BS-HA-FD-NEAT outperforms its ancestor by evolving significantly smaller networks. In overall, the resulting algorithm outperforms its ancestors, NEAT, FD-NEAT, and HA-NEAT achieving better accuracy, in fewer generations and evolving smaller and less complex networks. Finally, BS-HA-FD-NEAT is tested on a complex, real world application of reducing the false positives outputed from a detector of abnormal COVID-19 related findings from lung Computer Tomography (CT) images.
There are several online Q&A sessions organized before the start of the academic year – you will be informed and updated regarding this.
ETRO Prof Nikolaos Deligiannis was asked for a contribution to the Belgian Senate on Monday Jan 18. The hearing was focused on fake news in social media and representatives of Facebook and Google Belgium as well as from the EC were also present.
(The input from Nikos starts after 2:20h)