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...
Enregistré dans:
| Auteurs principaux: | Hidetaka Taniguchi, Hiroshi Sato, Tomohiro Shirakawa |
|---|---|
| Format: | article |
| Langue: | EN |
| Publié: |
Nature Portfolio
2018
|
| Sujets: | |
| Accès en ligne: | https://doaj.org/article/ce9a99c739bf4f4896c11549c24389ad |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
Self-incremental learning vector quantization with human cognitive biases
par: Nobuhito Manome, et autres
Publié: (2021) -
Reply to Letter to the Editor on “Not all biases are bad: equitable and inequitable biases in machine learning and radiology”
par: Mirjam Pot, et autres
Publié: (2021) -
Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
par: Dávid Péter Kovács, et autres
Publié: (2021) -
Measuring and mitigating PCR bias in microbiota datasets.
par: Justin D Silverman, et autres
Publié: (2021) -
GVES: machine learning model for identification of prognostic genes with a small dataset
par: Soohyun Ko, et autres
Publié: (2021)