Meta-learning (computer science): Difference between revisions

Content deleted Content added
m Fixing style/layout errors
LSTM Meta-Learner: Fixing a wikilink
Line 64:
 
====LSTM Meta-Learner====
[[LSTM]]-based meta-learner is to learn the exact [[optimization algorithm]] used to train another learner [[Artificial neural network|neural network]] [[classification rule|classifier]] in the few-shot regime. The parametrization allows it to learn appropriate parameter updates specifically for the scenario where a set amount of updates will be made, while also learning a general initialization of the learner (classifier) network that allows for quick convergence of training.<ref name="paper8">{{cite conference|url=https://openreview.net/pdf?id=rJY0-Kcll|first1=Sachin|last1=Ravi|first2=Hugo|last2=Larochelle|year=2017|title=Optimization as a model for few-shot learning|conference=ICLR 2017|access-date=3 November 2019|language=en}}</ref>
 
====Temporal Discreteness====