Self-Sustaining Iterated Learning

DOI10.4230/LIPICS.ITCS.2017.17MaRDI QIDQ4638066zbMATH OpenFDO

Authors Chu Wang, Bernard Chazelle

Publication date 3 May 2018

Full work available at URL https://arxiv.org/abs/1609.03960

zbMATH Keywords

non-equilibrium dynamicslanguage evolutioniterated learningiterated Bayesian linear regression

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Natural language processing (68T50)

Abstract: An important result from psycholinguistics (Griffiths & Kalish, 2005) states that no language can be learned iteratively by rational agents in a self-sustaining manner. We show how to modify the learning process slightly in order to achieve self-sustainability. Our work is in two parts. First, we characterize iterated learnability in geometric terms and show how a slight, steady increase in the lengths of the training sessions ensures self-sustainability for any discrete language class. In the second part, we tackle the nondiscrete case and investigate self-sustainability for iterated linear regression. We discuss the implications of our findings to issues of non-equilibrium dynamics in natural algorithms.

Recommendations

• Self-consistent learning of the environment
• Publication:4861477
• Autonomous learning with complex dynamics
• Variants of iterative learning
• Self-Improving Algorithms
• Self-improving algorithms
• A randomized stochastic approximation algorithm for self-learning

Cites work

• scientific article; zbMATH DE number 3103174 (Why is no real title available?)
• Eigenvalues and Condition Numbers of Random Matrices
• Encyclopedia of mathematics. Springer online reference works
• Local operator theory, random matrices and Banach spaces.
• Markov Chains
• Smallest singular value of a random rectangular matrix

Cited in

(3)

• Infinitary self-reference in learning theory
• Iterated learning in dynamic social networks
• Adding population structure to models of language evolution by iterated learning

This page was built for publication: Self-Sustaining Iterated Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4638066)