Achref Jaziri

Center of Computation and Cognition, Frankfurt University

ProfilePic1.jpg

Room S2|210

Robert Mayer Str.10-12

Frankfurt am Main, Germany

I am a PhD candidate in the Center for Computation and Cognition at Goethe University Frankfurt. My research focuses on the design of robust artificial intelligence (AI) systems based on principles of systems engineering. During my doctoral studies, I will be investigating topics that lie at the intersection of causality, continual learning, and the development of robust online systems. Additionally, I am particularly interested in the application of continually evolving systems to real-world problems within the scope of the KIBA project. Prior to my PhD, I successfully completed a Master's Degree in Computer Science with a specialization in Theoretical Neuroscience. During this time, I gained experience in the development and validation of computer vision models, as well as the creation of simulation tools for analyzing concrete defects, as part of the EU H2020 RESIST project (RE- Silient transport InfraSTructure to extreme events).

news

Jan, 2023 Officially joined the KIBA project.
Oct, 2023 Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation has been accepted to WACV2024.
Nov, 2023 Preprint for the Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning is out on Arxiv.
Dec, 2023 Lightweight Techniques to Improve Generalization and Robustness of U-Net Based Networks for Pulmonary Lobe Segmentation has been accepted in Bioengineering Journal.
Jan, 2024 Attending WACV2024.
Aug, 2024 Preprint for Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion is out on Arxiv.
Aug, 2024 ‘Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning’ has been accepted to the ECCV 2024 Human Inspired Vision Workshop.
Sept, 2024 Attending ECCV 2024.

Publications

  1. Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion
    Achref Jaziri, Etienne Künzel, Visvanathan Ramesh Under Review , August, 2024
  1. Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning
    A. Jaziri, S.Ditzel, I.Pliushch, Visvanathan Ramesh ECCV 2024 Workshops,, 2024
  1. Lightweight Techniques to Improve Generalization and Robustness of U-Net Based Networks for Pulmonary Lobe Segmentation
    Armin A Dadras, Achref Jaziri, Eric Frodl, Thomas J Vogl, Julia Dietz, Andreas M Bucher Bioengineering , Dec, 2023
  1. Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation
    A. Jaziri, M.Mundt, A. Rodriguez, Visvanathan Ramesh Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , Jan 2024
You can best reach me via Email. I will try to answer as soon as possible :)