Projects per year
Industry PhD student at Sony and LTH. Funded in the WASP initiative.
The project is starting in computer vision and image analysis to become familiar with current methods and a well established domain. This is used as an arena to find a machine task that involves human interaction and a non-static environment that allows incremental learning. Designing the task and learning process to benefit from transparency of the agent decisions (explainability) is a secondary goal.
While deep learning with large amounts of up-front learning data has made recent success, an agent that is able to learn incrementally from data available during usage should be more versatile. A human-in-the-loop approach, where the user is taking an active part in the learning or acting process, could be one way to give transparency but the human should not become a bottle-neck with no added value.
Working for Sony Europe in Lund and has been involved in different aspects of software development for mobile phones since 2001.
- 1 Similar Profiles
Dive into details
Select a country/territory to view shared publications and projects
- 1 Active
Incremental Learning Agents and Human Interaction
Gulin, J., Åström, K., Larsson, J. E. & Huang, S.
2019/01/01 → …
- 1 Participation in workshop/ seminar/ course
WASP Graduate School (any year)
Jens Gulin (Participant)2019 Jan 1 → …
Activity: Participating in or organising an event › Participation in workshop/ seminar/ course