Self-incremental learning vector quantization with human cognitive biases

Abstract Human beings have adaptively rational cognitive biases for efficiently acquiring concepts from small-sized datasets. With such inductive biases, humans can generalize concepts by learning a small number of samples. By incorporating human cognitive biases into learning vector quantization (L...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nobuhito Manome, Shuji Shinohara, Tatsuji Takahashi, Yu Chen, Ung-il Chung
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/217e4b2b43ed42cc944849d1cacb86f7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:217e4b2b43ed42cc944849d1cacb86f7
record_format	dspace
spelling	oai:doaj.org-article:217e4b2b43ed42cc944849d1cacb86f72021-12-02T12:11:53ZSelf-incremental learning vector quantization with human cognitive biases10.1038/s41598-021-83182-42045-2322https://doaj.org/article/217e4b2b43ed42cc944849d1cacb86f72021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83182-4https://doaj.org/toc/2045-2322Abstract Human beings have adaptively rational cognitive biases for efficiently acquiring concepts from small-sized datasets. With such inductive biases, humans can generalize concepts by learning a small number of samples. By incorporating human cognitive biases into learning vector quantization (LVQ), a prototype-based online machine learning method, we developed self-incremental LVQ (SILVQ) methods that can be easily interpreted. We first describe a method to automatically adjust the learning rate that incorporates human cognitive biases. Second, SILVQ, which self-increases the prototypes based on the method for automatically adjusting the learning rate, is described. The performance levels of the proposed methods are evaluated in experiments employing four real and two artificial datasets. Compared with the original learning vector quantization algorithms, our methods not only effectively remove the need for parameter tuning, but also achieve higher accuracy from learning small numbers of instances. In the cases of larger numbers of instances, SILVQ can still achieve an accuracy that is equal to or better than those of existing representative LVQ algorithms. Furthermore, SILVQ can learn linearly inseparable conceptual structures with the required and sufficient number of prototypes without overfitting.Nobuhito ManomeShuji ShinoharaTatsuji TakahashiYu ChenUng-il ChungNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Nobuhito Manome Shuji Shinohara Tatsuji Takahashi Yu Chen Ung-il Chung Self-incremental learning vector quantization with human cognitive biases
description	Abstract Human beings have adaptively rational cognitive biases for efficiently acquiring concepts from small-sized datasets. With such inductive biases, humans can generalize concepts by learning a small number of samples. By incorporating human cognitive biases into learning vector quantization (LVQ), a prototype-based online machine learning method, we developed self-incremental LVQ (SILVQ) methods that can be easily interpreted. We first describe a method to automatically adjust the learning rate that incorporates human cognitive biases. Second, SILVQ, which self-increases the prototypes based on the method for automatically adjusting the learning rate, is described. The performance levels of the proposed methods are evaluated in experiments employing four real and two artificial datasets. Compared with the original learning vector quantization algorithms, our methods not only effectively remove the need for parameter tuning, but also achieve higher accuracy from learning small numbers of instances. In the cases of larger numbers of instances, SILVQ can still achieve an accuracy that is equal to or better than those of existing representative LVQ algorithms. Furthermore, SILVQ can learn linearly inseparable conceptual structures with the required and sufficient number of prototypes without overfitting.
format	article
author	Nobuhito Manome Shuji Shinohara Tatsuji Takahashi Yu Chen Ung-il Chung
author_facet	Nobuhito Manome Shuji Shinohara Tatsuji Takahashi Yu Chen Ung-il Chung
author_sort	Nobuhito Manome
title	Self-incremental learning vector quantization with human cognitive biases
title_short	Self-incremental learning vector quantization with human cognitive biases
title_full	Self-incremental learning vector quantization with human cognitive biases
title_fullStr	Self-incremental learning vector quantization with human cognitive biases
title_full_unstemmed	Self-incremental learning vector quantization with human cognitive biases
title_sort	self-incremental learning vector quantization with human cognitive biases
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/217e4b2b43ed42cc944849d1cacb86f7
work_keys_str_mv	AT nobuhitomanome selfincrementallearningvectorquantizationwithhumancognitivebiases AT shujishinohara selfincrementallearningvectorquantizationwithhumancognitivebiases AT tatsujitakahashi selfincrementallearningvectorquantizationwithhumancognitivebiases AT yuchen selfincrementallearningvectorquantizationwithhumancognitivebiases AT ungilchung selfincrementallearningvectorquantizationwithhumancognitivebiases
_version_	1718394559956779008

Self-incremental learning vector quantization with human cognitive biases

Ejemplares similares