Unlearn What You Have Learned: Adaptive Crowd Teaching with Exponentially Decayed Memory Learners

-- Yao Zhou, Arun Reddy Nelakurthi, Jingrui He

Introduction

We propose an adaptive teaching framework named JEDI to construct the personalized optimal teaching set for the crowdsourcing workers. The paper is available at here.

Content

• Matlab implementation of JEDI with harmonic function estimation.
• Django/Python implementation of the JEDI adaptive web interface for real human learners.

Reference

If you find that JEDI is helpful in your research, please consider to cite our paper:

  @InProceedings{YaoZhouKDD18,
	author={Yao Zhou and Arun Reddy Nelakurthi and Jingrui He},
	title={Unlearn What You Have Learned: Adaptive Crowd Teaching with Exponentially Decayed Memory Learners},
	booktitle={KDD},
	pages={2817--2826},
	year={2018}
  }

Acknowledgement

This is the latest source code of JEDI for KDD 18.

Copyright(c) Yao Zhou and Arun Reddy Nelakurthi all rights reserved.