Model-based learning problem taxonomies

Behavioral and Brain Sciences 20 (1):73-74 (1997)
  Copy   BIBTEX

Abstract

A fundamental problem with the Clark & Thornton definition of a type-1 problem (requirement 2) is identified. An alternative classical statistical formulation is proposed where a type-1 (learnable) problem corresponds to the case where the learning machine is capable of representing its statistical environment.

Other Versions

No versions found

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 100,561

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

What is the type-1/type-2 distinction?Nick Chater - 1997 - Behavioral and Brain Sciences 20 (1):68-69.
Taming type-2 tigers: A nonmonotonic strategy.István S. N. Berkeley - 1997 - Behavioral and Brain Sciences 20 (1):66-67.
Parity is not a generalisation problem.R. I. Damper - 1997 - Behavioral and Brain Sciences 20 (1):69-70.
Reducing problem complexity by analogical transfer.Peter F. Dominey - 1997 - Behavioral and Brain Sciences 20 (1):71-72.
How Values Shape the Machine Learning Opacity Problem.Emily Sullivan - 2022 - In Insa Lawler, Kareem Khalifa & Elay Shech (eds.), Scientific Understanding and Representation: Modeling in the Physical Sciences. New York, NY: Routledge. pp. 306-322.
Extracting higher-level relationships in connectionist models.Gary F. Marcus - 1997 - Behavioral and Brain Sciences 20 (1):77-77.
Old ideas, new mistakes: All learning is relational.Stellan Ohlsson - 1997 - Behavioral and Brain Sciences 20 (1):79-80.

Analytics

Added to PP
2009-01-28

Downloads
47 (#453,169)

6 months
14 (#210,560)

Historical graph of downloads
How can I increase my downloads?

Citations of this work

No citations found.

Add more citations

References found in this work

No references found.

Add more references