Interactive Machine Learning via Adaptive Submodularity
Event details
| Date | 11.06.2014 |
| Hour | 14:00 |
| Speaker | Andreas KRAUSE, ETH Zürich |
| Location | |
| Category | Conferences - Seminars |
How can people and machines cooperate to gain insight and discover useful information from complex data sets? A central challenge lies in optimizing the interaction, which leads to difficult sequential decision problems under uncertainty. In this talk, I will introduce the new concept of adaptive submodularity, generalizing the classical notion of submodular set functions to adaptive policies. We prove that if a problem satisfies this property, a simple adaptive greedy algorithm is guaranteed to be competitive with the optimal policy.
The concept allows to recover, generalize and extend existing results in diverse domains including active learning, resource allocation and social network analysis. I will show results on several real-world applications, ranging from interactive content search over image categorization in citizen science to biodiversity monitoring via conservation drones.
The concept allows to recover, generalize and extend existing results in diverse domains including active learning, resource allocation and social network analysis. I will show results on several real-world applications, ranging from interactive content search over image categorization in citizen science to biodiversity monitoring via conservation drones.
Links
Practical information
- General public
- Free
Organizer
- Rüdiger Urbanke
Contact
- Sylvie Thomet