A machine learning model with human cognitive biases capable of learning from small and biased datasets

Abstract Human learners can generalize a new concept from a small number of samples. In contrast, conventional machine learning methods require large amounts of data to address the same types of problems. Humans have cognitive biases that promote fast learning. Here, we developed a method to reduce...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hidetaka Taniguchi, Hiroshi Sato, Tomohiro Shirakawa
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2018
Materias:
R
Q
Acceso en línea:https://doaj.org/article/ce9a99c739bf4f4896c11549c24389ad
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ce9a99c739bf4f4896c11549c24389ad
record_format dspace
spelling oai:doaj.org-article:ce9a99c739bf4f4896c11549c24389ad2021-12-02T12:33:00ZA machine learning model with human cognitive biases capable of learning from small and biased datasets10.1038/s41598-018-25679-z2045-2322https://doaj.org/article/ce9a99c739bf4f4896c11549c24389ad2018-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-25679-zhttps://doaj.org/toc/2045-2322Abstract Human learners can generalize a new concept from a small number of samples. In contrast, conventional machine learning methods require large amounts of data to address the same types of problems. Humans have cognitive biases that promote fast learning. Here, we developed a method to reduce the gap between human beings and machines in this type of inference by utilizing cognitive biases. We implemented a human cognitive model into machine learning algorithms and compared their performance with the currently most popular methods, naïve Bayes, support vector machine, neural networks, logistic regression and random forests. We focused on the task of spam classification, which has been studied for a long time in the field of machine learning and often requires a large amount of data to obtain high accuracy. Our models achieved superior performance with small and biased samples in comparison with other representative machine learning methods.Hidetaka TaniguchiHiroshi SatoTomohiro ShirakawaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-13 (2018)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Hidetaka Taniguchi
Hiroshi Sato
Tomohiro Shirakawa
A machine learning model with human cognitive biases capable of learning from small and biased datasets
description Abstract Human learners can generalize a new concept from a small number of samples. In contrast, conventional machine learning methods require large amounts of data to address the same types of problems. Humans have cognitive biases that promote fast learning. Here, we developed a method to reduce the gap between human beings and machines in this type of inference by utilizing cognitive biases. We implemented a human cognitive model into machine learning algorithms and compared their performance with the currently most popular methods, naïve Bayes, support vector machine, neural networks, logistic regression and random forests. We focused on the task of spam classification, which has been studied for a long time in the field of machine learning and often requires a large amount of data to obtain high accuracy. Our models achieved superior performance with small and biased samples in comparison with other representative machine learning methods.
format article
author Hidetaka Taniguchi
Hiroshi Sato
Tomohiro Shirakawa
author_facet Hidetaka Taniguchi
Hiroshi Sato
Tomohiro Shirakawa
author_sort Hidetaka Taniguchi
title A machine learning model with human cognitive biases capable of learning from small and biased datasets
title_short A machine learning model with human cognitive biases capable of learning from small and biased datasets
title_full A machine learning model with human cognitive biases capable of learning from small and biased datasets
title_fullStr A machine learning model with human cognitive biases capable of learning from small and biased datasets
title_full_unstemmed A machine learning model with human cognitive biases capable of learning from small and biased datasets
title_sort machine learning model with human cognitive biases capable of learning from small and biased datasets
publisher Nature Portfolio
publishDate 2018
url https://doaj.org/article/ce9a99c739bf4f4896c11549c24389ad
work_keys_str_mv AT hidetakataniguchi amachinelearningmodelwithhumancognitivebiasescapableoflearningfromsmallandbiaseddatasets
AT hiroshisato amachinelearningmodelwithhumancognitivebiasescapableoflearningfromsmallandbiaseddatasets
AT tomohiroshirakawa amachinelearningmodelwithhumancognitivebiasescapableoflearningfromsmallandbiaseddatasets
AT hidetakataniguchi machinelearningmodelwithhumancognitivebiasescapableoflearningfromsmallandbiaseddatasets
AT hiroshisato machinelearningmodelwithhumancognitivebiasescapableoflearningfromsmallandbiaseddatasets
AT tomohiroshirakawa machinelearningmodelwithhumancognitivebiasescapableoflearningfromsmallandbiaseddatasets
_version_ 1718393885930029056