Dr. Hamed Ayoobi

Summary

I am a research associate in the Department of Computing working on the ADIX (Argumentation-based Deep Interactive eXplanations) project. My academic pursuits primarily revolve around the fields of eXplainable Artificial Intelligence (XAI), Robotic Vision, and Argumentation. Specifically, my research focuses on elucidating the inner workings of deep neural models applied to multi-modal data, encompassing tabular, image, and textual information. Additionally, I harbour a keen fascination for the integration of explainable models into robotic systems that operate within dynamic environments, necessitating continuous, adaptive learning to accommodate the ever-changing conditions of their surroundings.

Before joining Imperial in 2022, I was a PhD student at the University of Groningen, The Netherlands.

Selected Publications

• Journal Article
  H. Ayoobi, M. Cao, R. Verbrugge and B. Verheij, "Argumentation-Based Online Incremental Learning," in IEEE Transactions on Automation Science and Engineering, vol. 19, no. 4, pp. 3419-3433, Oct. 2022. (URL)
  
  H. Ayoobi , H. Kasaei, M. Cao, R. Verbrugge, and B. Verheij. "Local-HDP: Interactive open-ended 3D object category recognition in real-time robotic scenarios", in Robotics and Autonomous Systems, vol. 147,103911, 2022. (URL)
  
  
• Conference
  Ayoobi, H., Potyka, N., Toni, F. (2023 Oct).
  SpArX: Sparse Argumentative Explanations for Neural Networks. In 2023 26th European Conference on Artificial Intelligence (ECAI). (URL)
  
  Ayoobi, H., Kasaei, H., Cao, M., Verbrugge, R., & Verheij, B. (2023, May). Explain What You See: Open-Ended Segmentation and Recognition of Occluded 3D Objects. In 2023 IEEE International Conference on Robotics and Automation (ICRA). (URL)
  
  Ayoobi, H., Cao, M., Verbrugge, R., & Verheij, B. (2021, December). Argue to Learn: Accelerated Argumentation-Based Learning. In 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 1118-1123). IEEE. (URL)
  
  Ayoobi, H., Cao, M., Verbrugge, R., & Verheij, B. (2019, August). Handling unforeseen failures using argumentation-based learning. In 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE) (pp. 1699-1704). IEEE. (URL)
• ArXiv:
  Ayoobi, H., Potyka, N., & Toni, F. (2023). ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation. arXiv preprint arXiv:2311.15438.
  
  Dejl, A., Ayoobi, H., Williams, M., & Toni, F. (2023). CAFE: Conflict-Aware Feature-wise Explanations. arXiv preprint arXiv:2310.20363.
  
  Van der Velde, T., Ayoobi, H.,& Kasaei, H. (2023). GraspCaps: A Capsule Network Approach for Familiar 6DoF Object Grasping. arXiv preprint arXiv:2210.03628.

Publications

Conference

More Publications