Learning by Teaching, with Application to Neural Architecture Search

@article{Sheth2021LearningBT,
  title={Learning by Teaching, with Application to Neural Architecture Search},
  author={Parth Sheth and Y. Jiang and P. Xie},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.07009}
}
In human learning, an effective skill in improving learning outcomes is learning by teaching: a learner deepens his/her understanding of a topic by teaching this topic to others. In this paper, we aim to borrow this teaching-driven learning methodology from humans and leverage it to train more performant machine learning models, by proposing a novel ML framework referred to as learning by teaching (LBT). In the LBT framework, a teacher model improves itself by teaching a student model to learn… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 46 REFERENCES
Search for Better Students to Learn Distilled Knowledge
Neural Architecture Search with Reinforcement Learning
Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation
Efficient Neural Architecture Search via Parameter Sharing
Distilling the Knowledge in a Neural Network
Progressive Neural Architecture Search
Searching for a Robust Neural Architecture in Four GPU Hours
  • Xuanyi Dong, Yezhou Yang
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
...
1
2
3
4
5
...