Meta-learning (computer science): Difference between revisions

Content deleted Content added
Adding local short description: "Subfield of machine learning", overriding Wikidata description "subfield of Machine learning" (Shortdesc helper)
m Common approaches: fixed list
Line 27:
 
==Common approaches==
There are three common approaches: 1)using (cyclic) networks with external or internal memory (model-based); 2)learning effective distance metrics (metrics-based); 3)explicitly optimizing model parameters for fast learning (optimization-based).<ref name="paper1">[https://lilianweng.github.io/lil-log/2018/11/30/meta-learning.html] Lilian Weng(2018). Meta-Learning: Learning to Learn Fast. OpenAI Blog . November 2018 . Retrieved 27 October 2019</ref>
* 1) using (cyclic) networks with external or internal memory (model-based)
* 2) learning effective distance metrics (metrics-based)
* 3) explicitly optimizing model parameters for fast learning (optimization-based).
 
===Model-Based===