`Less Than One'-Shot Learning: Learning N Classes From M < N Samples

Authors

  • Ilia Sucholutsky University of Waterloo
  • Matthias Schonlau University of Waterloo

Keywords:

Multi-class/Multi-label Learning & Extreme Classification, (Deep) Neural Network Learning Theory, Other Foundations of Machine Learning

Abstract

Deep neural networks require large training sets but suffer from high computational cost and long training times. Training on much smaller training sets while maintaining nearly the same accuracy would be very beneficial. In the few-shot learning setting, a model must learn a new class given only a small number of samples from that class. One-shot learning is an extreme form of few-shot learning where the model must learn a new class from a single example. We propose the 'less than one'-shot learning task where models must learn N new classes given only M

Downloads

Published

2021-05-18

How to Cite

Sucholutsky, I., & Schonlau, M. (2021). `Less Than One’-Shot Learning: Learning N Classes From M < N Samples. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 9739-9746. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17171

Issue

Section

AAAI Technical Track on Machine Learning IV