Learning to benchmark is coming at 04/27/2020 - 4:00pm

KEC 1001
Mon, 04/27/2020 - 4:00pm

Alfred O. Hero III
   John H. Holland Distinguished University Professor of Electrical 
Engineering
and Computer Science, R. Jamison and Betty Williams Professor of Engineering,
University of Michigan, Ann Arbor

Abstract:
We address the problem of learning an achievable lower bound on
classification error from a labeled sample. We establish a framework for this
meta-learning problem, which we call benchmark learning. Benchmark learning
leads to an accurate data-driven predictor of performance of a Bayes optimal
classifier without having to construct the classifier and without assuming
any parametric model for the data. The resultant predictor can be used to
establish whether it is possible to improve classification performance of a
specific classifier. It also yields a stopping rule for sequentially trained
classifiers. In addition, The talk will cover relevant background, theory,
algorithms, and applications of benchmark learning.

Bio:


Read more: https://eecs.oregonstate.edu/colloquium/learning-benchmark [1]

[1] https://eecs.oregonstate.edu/colloquium/learning-benchmark
_______________________________________________
Colloquium mailing list
[email protected]
https://secure.engr.oregonstate.edu/mailman/listinfo/colloquium
  • [EECS Colloquium] ... School of Electrical Engineering & Computer Science
    • [EECS Colloqu... School of Electrical Engineering & Computer Science

Reply via email to