PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE.

Leonard Pitt, Carl H. Smith

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A notion of probabilistic team inductive inference is introduced and compared with both probabilistic inference and team inference. In many cases, but not all, probabilism can be traded for pluralism, and vice versa. Necessary and sufficient conditions are given that determine when a team of deterministic or probabilistic learning machines can be coalesced into a single learning machine. A subtle difference between probabilism and pluralism is revealed.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Circuits, Systems & Computers
PublisherIEEE
Pages346-350
Number of pages5
ISBN (Print)0818608161
StatePublished - Jan 1 1987

Publication series

NameConference Record - Asilomar Conference on Circuits, Systems & Computers
ISSN (Print)0736-5861

Fingerprint

Learning systems

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Pitt, L., & Smith, C. H. (1987). PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE. In Conference Record - Asilomar Conference on Circuits, Systems & Computers (pp. 346-350). (Conference Record - Asilomar Conference on Circuits, Systems & Computers). IEEE.

PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE. / Pitt, Leonard; Smith, Carl H.

Conference Record - Asilomar Conference on Circuits, Systems & Computers. IEEE, 1987. p. 346-350 (Conference Record - Asilomar Conference on Circuits, Systems & Computers).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pitt, L & Smith, CH 1987, PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE. in Conference Record - Asilomar Conference on Circuits, Systems & Computers. Conference Record - Asilomar Conference on Circuits, Systems & Computers, IEEE, pp. 346-350.
Pitt L, Smith CH. PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE. In Conference Record - Asilomar Conference on Circuits, Systems & Computers. IEEE. 1987. p. 346-350. (Conference Record - Asilomar Conference on Circuits, Systems & Computers).
Pitt, Leonard ; Smith, Carl H. / PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE. Conference Record - Asilomar Conference on Circuits, Systems & Computers. IEEE, 1987. pp. 346-350 (Conference Record - Asilomar Conference on Circuits, Systems & Computers).
@inproceedings{9c497cc4f3ef42e593c1a00329bda47e,
title = "PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE.",
abstract = "A notion of probabilistic team inductive inference is introduced and compared with both probabilistic inference and team inference. In many cases, but not all, probabilism can be traded for pluralism, and vice versa. Necessary and sufficient conditions are given that determine when a team of deterministic or probabilistic learning machines can be coalesced into a single learning machine. A subtle difference between probabilism and pluralism is revealed.",
author = "Leonard Pitt and Smith, {Carl H.}",
year = "1987",
month = "1",
day = "1",
language = "English (US)",
isbn = "0818608161",
series = "Conference Record - Asilomar Conference on Circuits, Systems & Computers",
publisher = "IEEE",
pages = "346--350",
booktitle = "Conference Record - Asilomar Conference on Circuits, Systems & Computers",

}

TY - GEN

T1 - PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE.

AU - Pitt, Leonard

AU - Smith, Carl H.

PY - 1987/1/1

Y1 - 1987/1/1

N2 - A notion of probabilistic team inductive inference is introduced and compared with both probabilistic inference and team inference. In many cases, but not all, probabilism can be traded for pluralism, and vice versa. Necessary and sufficient conditions are given that determine when a team of deterministic or probabilistic learning machines can be coalesced into a single learning machine. A subtle difference between probabilism and pluralism is revealed.

AB - A notion of probabilistic team inductive inference is introduced and compared with both probabilistic inference and team inference. In many cases, but not all, probabilism can be traded for pluralism, and vice versa. Necessary and sufficient conditions are given that determine when a team of deterministic or probabilistic learning machines can be coalesced into a single learning machine. A subtle difference between probabilism and pluralism is revealed.

UR - http://www.scopus.com/inward/record.url?scp=0023171841&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023171841&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0023171841

SN - 0818608161

T3 - Conference Record - Asilomar Conference on Circuits, Systems & Computers

SP - 346

EP - 350

BT - Conference Record - Asilomar Conference on Circuits, Systems & Computers

PB - IEEE

ER -