Learning and the Structure of Information.

Dean T. Jamison, D. Lhamon, P. Suppes

Expert InsightsPublished 1969

A preliminary study to (1) bring together the ideas of mathematical learning theory and the concept of information structure, and (2) show the difficulty of analyzing these concepts for explicit, experimentally testable results. Three theories are discussed: (1) Paired-associate learning; eight existing and several new theories are presented, including, for each new theory, its assumptions, basic mathematical structure, some derivations, and its relation to other theories. (2) Probability learning; two essentially all-or-none theories and a linear theory are presented. (3) General information structures where the set of possible reinforcements has more than two subsets, which are equivalence classes with respect to their value to the subject. Findings indicate that the mathematical models of learning are awkward to handle with any but the simplest information structures on reinforcing effects, although a number of analytic results are obtained. 83 pp. Ref.

Document Details

  • Copyright: RAND Corporation
  • Availability: Web Only
  • Year: 1969
  • Pages: 83
  • Document Number: P-4092

Citation

Chicago Manual of Style

Jamison, Dean T., D. Lhamon, and P. Suppes, Learning and the Structure of Information. Santa Monica, CA: RAND Corporation, 1969. https://www.rand.org/pubs/papers/P4092.html.
BibTeX RIS

This publication is part of the RAND paper series. The paper series was a product of RAND from 1948 to 2003 that captured speeches, memorials, and derivative research, usually prepared on authors' own time and meant to be the scholarly or scientific contribution of individual authors to their professional fields. Papers were less formal than reports and did not require rigorous peer review.

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit www.rand.org/pubs/permissions.

RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.