Search Results for author: Yonatan Geifman

Found 6 papers, 2 papers with code

SelectiveNet: A Deep Neural Network with an Integrated Reject Option

4 code implementations26 Jan 2019 Yonatan Geifman, Ran El-Yaniv

We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option.

Classification General Classification +1

Deep Active Learning over the Long Tail

no code implementations2 Nov 2017 Yonatan Geifman, Ran El-Yaniv

This paper is concerned with pool-based active learning for deep neural networks.

Active Learning

The Prediction Advantage: A Universally Meaningful Performance Measure for Classification and Regression

no code implementations23 May 2017 Ran El-Yaniv, Yonatan Geifman, Yair Wiener

We introduce the Prediction Advantage (PA), a novel performance measure for prediction functions under any loss function (e. g., classification or regression).

General Classification imbalanced classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.