Rishi Hazra
Befattning: Doktorand Organisation: Institutionen för naturvetenskap och teknikE-post: rishi.hazra@oru.se
Telefon: Telefonnummer saknas
Rum: T2245
Om Rishi Hazra
I am enrolled as a first-year Ph.D. student through the Wallenberg AI, Autonomous Systems and Software Program (WASP) graduate school, under the supervision of Professor Luc De Raedt.
Broadly, my area of research lies in developing systems that learn and reason in an artificial intelligence and autonomous systems context using both data-driven and knowledge-based approaches. My goal is to develop planning modules and neuro-symbolic approaches and apply them to autonomous sensor systems.
I completed my Masters in Artificial Intelligence from Indian Institute of Science (IISc), Bangalore in 2019. My thesis was on Active Learning for NLP applications. Post that, I worked as a Research Associate in the Statistics and Machine Learning Group (IISc) with my primary focus on Multi-Agent Reinforcement Learning. Before joining as a doctoral student in Örebro, I was working in Amazon Alexa-AI Bangalore with the Natural Language Understanding group.
Forskargrupper
Publikationer
Konferensbidrag
- Hazra, R. & De Raedt, L. (2023). Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach. I: Danai Koutra; Claudia Plant; Manuel Gomez Rodriguez; Elena Baralis; Francesco Bonchi, Machine Learning and Knowledge Discovery in Databases: Research Track European Conference, ECML PKDD 2023, Turin, Italy, September 18–22, 2023, Proceedings, Part IV. Konferensbidrag vid European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2023), Turin, Italy, September 18-22, 2023. (ss. 213-229). Springer.
- Hazra, R. , Chen, B. , Rai, A. , Kamra, N. & Desai, R. (2023). EgoTV: Egocentric Task Verification from Natural Language Task Descriptions. I: 2023 IEEE/CVF International Conference on Computer Vision (ICCV) Proceedings. Konferensbidrag vid International Conference on Computer Vision (ICCV 2023), Paris, France, October 2-6, 2023. (ss. 15371-15383). IEEE.