Please I will need your help, I want to do a project on active learning to help a company reduce the cost of getting enough labelled data for their classifiers
Our #ICLR2019 paper on #activelearning with partial feedback. It is expensive to obtain full information from labeler: e.g. picking fine-grained category. Can the algorithm actively decide what to ask labeler? Can we move on to a different example in a strategic way?https://twitter.com/HuPeiyun/status/1087745819086745600 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
We have some work on what we call as"active advice seeking". The goal here is to go being just labels and get richer forms of inputs such as preferences or qualitative constraints. Have been pursuing this in the context of graphical models, planning and RL
-
The key challenge is not just when to ask but what to ask
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.