A boundedly rational model for category learning
Troy M. Houser · 2024
Read A boundedly rational model for category learning by Troy M. Houser (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11663663.txt.
Description
Troy Houser offers a model of category learning that weighs accuracy against cost, in a 2024 paper. Most models are judged only on how well they sort items into groups. Sharp internal representations sort well, but real minds face noise. Noise makes choices less certain, and cutting noise takes mental effort.
Houser builds an autoencoder model that learns six categories under this trade-off. The model can spend resources to sharpen its representations. It can also accept some noise and save the effort. Results show how a boundedly rational learner balances the two. The approach gives a more lifelike account of human sorting. It also hints at why people settle for good enough answers.
Catalog record
| CREATOR | Troy M. Houser |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |