Meta-learners' learning dynamics are unlike learners'

@article{Rabinowitz2019MetalearnersLD,
  title={Meta-learners' learning dynamics are unlike learners'},
  author={Neil C. Rabinowitz},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.01320}
}
Meta-learning is a tool that allows us to build sample-efficient learning systems. Here we show that, once meta-trained, LSTM Meta-Learners aren’t just faster learners than their sampleinefficient deep learning (DL) and reinforcement learning (RL) brethren, but that they actually pursue fundamentally different learning trajectories. We study their learning dynamics on three sets of structured tasks for which the corresponding learning dynamics of DL and RL systems have been previously described… CONTINUE READING
12
Twitter Mentions

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-2 OF 2 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 112 REFERENCES

A mathematical theory of semantic development in deep neural networks

  • Proceedings of the National Academy of Sciences of the United States of America
  • 2019
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL