TY - GEN
T1 - PROBABILISM AND PLURALISM IN INDUCTIVE INFERENCE.
AU - Pitt, Leonard
AU - Smith, Carl H.
PY - 1987
Y1 - 1987
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 -