Creating A Memory of Causal Relationships

An Integration of Empirical and Explanation-based Learning Methods

Nonfiction, Health & Well Being, Psychology, Cognitive Psychology
Cover of the book Creating A Memory of Causal Relationships by Michael J. Pazzani, Taylor and Francis
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Michael J. Pazzani ISBN: 9781317783916
Publisher: Taylor and Francis Publication: February 25, 2014
Imprint: Psychology Press Language: English
Author: Michael J. Pazzani
ISBN: 9781317783916
Publisher: Taylor and Francis
Publication: February 25, 2014
Imprint: Psychology Press
Language: English

This book presents a theory of learning new causal relationships by making use of perceived regularities in the environment, general knowledge of causality, and existing causal knowledge. Integrating ideas from the psychology of causation and machine learning, the author introduces a new learning procedure called theory-driven learning that uses abstract knowledge of causality to guide the induction process.

Known as OCCAM, the system uses theory-driven learning when new experiences conform to common patterns of causal relationships, empirical learning to learn from novel experiences, and explanation-based learning when there is sufficient existing knowledge to explain why a new outcome occurred. Together these learning methods construct a hierarchical organized memory of causal relationships. As such, OCCAM is the first learning system with the ability to acquire, via empirical learning, the background knowledge required for explanation-based learning.

Please note: This program runs on common lisp.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

This book presents a theory of learning new causal relationships by making use of perceived regularities in the environment, general knowledge of causality, and existing causal knowledge. Integrating ideas from the psychology of causation and machine learning, the author introduces a new learning procedure called theory-driven learning that uses abstract knowledge of causality to guide the induction process.

Known as OCCAM, the system uses theory-driven learning when new experiences conform to common patterns of causal relationships, empirical learning to learn from novel experiences, and explanation-based learning when there is sufficient existing knowledge to explain why a new outcome occurred. Together these learning methods construct a hierarchical organized memory of causal relationships. As such, OCCAM is the first learning system with the ability to acquire, via empirical learning, the background knowledge required for explanation-based learning.

Please note: This program runs on common lisp.

More books from Taylor and Francis

Cover of the book Nationalism and Power Politics in Japan's Relations with China by Michael J. Pazzani
Cover of the book Sobriety & Mirth by Michael J. Pazzani
Cover of the book Revival: Mnemic Psychology (1923) by Michael J. Pazzani
Cover of the book Housing Need and the Need for Housing by Michael J. Pazzani
Cover of the book Planet Utopia by Michael J. Pazzani
Cover of the book Handbook of Indigenous Peoples' Rights by Michael J. Pazzani
Cover of the book Sense and Nonsense and the National Curriculum by Michael J. Pazzani
Cover of the book Infusing Vocabulary Into the Reading-Writing Workshop by Michael J. Pazzani
Cover of the book Learning Through Problem Solving by Michael J. Pazzani
Cover of the book Deciding Children's Futures by Michael J. Pazzani
Cover of the book Charlotte Brontë by Michael J. Pazzani
Cover of the book The Constitution of Liberty in the Open Economy by Michael J. Pazzani
Cover of the book Optimality in Biological and Artificial Networks? by Michael J. Pazzani
Cover of the book From Cape Town to Kabul by Michael J. Pazzani
Cover of the book Urbanization in a Federalist Context by Michael J. Pazzani
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy