Meta-learning (computer science): Difference between revisions

Revision as of 07:48, 7 May 2021

Revision as of 08:11, 27 June 2021

Line 24:

''Bias'' refers to the assumptions that influence the choice of explanatory hypotheses<ref>{{Cite book|title=Metalearning - Springer|doi=10.1007/978-3-540-73263-1|series = Cognitive Technologies|year = 2009|isbn = 978-3-540-73262-4|last1 = Brazdil|first1 = Pavel|last2=Carrier|first2=Christophe Giraud|last3=Soares|first3=Carlos|last4=Vilalta|first4=Ricardo}}</ref> and not the notion of bias represented in the [[bias-variance dilemma]]. Meta learning is concerned with two aspects of learning bias.

* Declarative bias specifies the representation of the space of hypotheses, and affects the size of the search space (e.g., represent hypotheses using linear functions only).

* Procedural bias imposes constraints on the ordering of the inductive hypotheses (e.g., preferring smaller hypotheses). <ref>{{cite journal |last1=Gordon |first1=Diana |last2=Desjardins |first2=Marie |title=Evaluation and Selection of Biases in Machine Learning |journal=Machine Learning |date=1995 |volume=20 |pages=5–22 |doi=10.1023/A:1022630017346 |url=https://link.springer.com/content/pdf/10.1023/A:1022630017346.pdf |access-date=27 March 2020|doi-access=free }}</ref>

==Common approaches==

Line 48:

====Matching Networks====

Matching Networks learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types.<ref name="paper5">[http://papers.nips.cc/paper/6385-matching-networks-for-one-shot-learning.pdf] Vinyals, O. , Blundell, C. , Lillicrap, T. , Kavukcuoglu, K. , & Wierstra, D. . (2016). Matching networks for one shot learning. Google DeepMind. Retrieved 3 November, 2019</ref>

====Relation Network====

Line 60:

====LSTM Meta-Learner====

LSTM-based meta-learner is to learn the exact [[optimization algorithm]] used to train another learner [[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">[https://openreview.net/pdf?id=rJY0-Kcll] Sachin Ravi∗and Hugo Larochelle(2017).” Optimization as a model for few-shot learning”. ICLR 2017. Retrieved 3 November, 2019</ref>

====Temporal Discreteness====

Line 66:

====Reptile====

Reptile is a remarkably simple meta-learning optimization algorithm, given that both of it'sits components rely on meta-optimization through gradient descent and both are model-agnostic.<ref name="paper10">[https://arxiv.org/abs/1803.02999] Chelsea Finn, Pieter Abbeel, Sergey Levine(2017). Alex Nichol and Joshua Achiam and John Schulman(2018).” On First-Order Meta-Learning Algorithms”. arXiv:1803.02999 [cs.LG]</ref>

==Examples==

Line 73:

* [[Recurrent neural networks]] (RNNs) are universal computers. In 1993, [[Jürgen Schmidhuber]] showed how "self-referential" RNNs can in principle learn by [[backpropagation]] to run their own weight change algorithm, which may be quite different from backpropagation.<ref name="sch1993">{{cite journal | last1 = Schmidhuber | first1 = Jürgen | year = 1993| title = A self-referential weight matrix | journal = Proceedings of ICANN'93, Amsterdam | pages = 446–451}}</ref> In 2001, [[Sepp Hochreiter]] & A.S. Younger & P.R. Conwell built a successful supervised meta learner based on [[Long short-term memory]] RNNs. It learned through backpropagation a learning algorithm for quadratic functions that is much faster than backpropagation.<ref name="hoch2001">{{cite journal | last1 = Hochreiter | first1 = Sepp | last2 = Younger | first2 = A. S. | last3 = Conwell | first3 = P. R. | year = 2001| title = Learning to Learn Using Gradient Descent | journal = Proceedings of ICANN'01| pages = 87–94}}</ref><ref name="scholarpedia" /> Researchers at [[Deepmind]] (Marcin Andrychowicz et al.) extended this approach to optimization in 2017.<ref name="marcin2017">{{cite journal | last1 = Andrychowicz | first1 = Marcin | last2 = Denil | first2 = Misha | last3 = Gomez | first3 = Sergio | last4 = Hoffmann | first4 = Matthew | last5 = Pfau | first5 = David | last6 = Schaul | first6 = Tom | last7 = Shillingford | first7 = Brendan | last8 = de Freitas | first8 = Nando | year = 2017| title = Learning to learn by gradient descent by gradient descent | journal = Proceedings of ICML'17, Sydney, Australia}}</ref>

* In the 1990s, Meta [[Reinforcement Learning]] or Meta RL was achieved in Schmidhuber's research group through self-modifying policies written in a universal programming language that contains special instructions for changing the policy itself. There is a single lifelong trial. The goal of the RL agent is to maximize reward. It learns to accelerate reward intake by continually improving its own learning algorithm which is part of the "self-referential" policy.<ref name="sch1994">{{cite journal | last1 = Schmidhuber | first1 = Jürgen | year = 1994| title = On learning how to learn learning strategies | journal = Technical Report FKI-198-94, Tech. Univ. Munich}}</ref><ref name="sch1997">{{cite journal | last1 = Schmidhuber | first1 = Jürgen | last2 = Zhao | first2 = J. | last3 = Wiering | first3 = M. | year = 1997| title = Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement | journal = Machine Learning | volume = 28 | pages = 105–130 | doi=10.1023/a:1007383707642| doi-access = free }}</ref>

* An extreme type of Meta [[Reinforcement Learning]] is embodied by the [[Gödel machine]], a theoretical construct which can inspect and modify any part of its own software which also contains a general [[Automated theorem proving|theorem prover]]. It can achieve [[recursive self-improvement]] in a provably optimal way.<ref name="goedelmachine">{{cite journal | last1 = Schmidhuber | first1 = Jürgen | year = 2006| title = Gödel machines: Fully Self-Referential Optimal Universal Self-Improvers | url=https://archive.org/details/arxiv-cs0309048| journal = In B. Goertzel & C. Pennachin, Eds.: Artificial General Intelligence | pages = 199–226}}</ref><ref name="scholarpedia" />

Line 93 ⟶ 92:

== External links ==

* [http://www.scholarpedia.org/article/Metalearning Metalearning] article in [[Scholarpedia]]

* Vilalta R. and Drissi Y. (2002). ''[http://axon.cs.byu.edu/Dan/478/misc/Vilalta.pdf A perspective view and survey of meta-learning]'', Artificial Intelligence Review, 18(2), 77—9577–95.

* Giraud-Carrier, C., & Keller, J. (2002). Dealing with the data flood, J. Meij (ed), chapter Meta-Learning. STT/Beweton, The Hague.

* Brazdil P., Giraud-Carrier C., Soares C., Vilalta R. (2009) [https://books.google.com/books?id=-Gsi_cxZGpcC&printsec=frontcover#v=onepage&q&f=false Metalearning: applications to data mining], chapter Metalearning: Concepts and Systems, Springer

* Video courses about Meta-Learning with step-by-step explanation of [https://www.youtube.com/watch?v=IkDw22a8BDE MAML], [https://www.youtube.com/watch?v=rHGPfl0pvLY Prototypical Networks], and [https://www.youtube.com/watch?v=j8qDaVfrO_c Relation Networks].

{{DEFAULTSORT:Meta Learning (Computer Science)}}