Descriptive Complexity Approaches to Inductive Inference

Simple item page
dc.contributor.authorAtteson, Kevin
dc.date2023-05-17T01:08:58.000
dc.date.accessioned2023-05-22T12:55:50Z
dc.date.available2023-05-22T12:55:50Z
dc.date.issued1991
dc.date.submitted2007-08-09T08:28:14-07:00
dc.description.abstractWe present a critical review of descriptive complexity approaches to inductive inference. Inductive inference is defined as any process by which a model of the world is formed from observations. The descriptive complexity approach is a formalization of Occam's razor: choose the simplest model consistent with the data. Descriptive complexity as defined by Kolmogorov, Chaitin and Solomonoff is presented as a generalization of Shannon's entropy. We discuss its relationship with randomness and present examples. However, a major result of the theory is negative: descriptive complexity is uncomputable. Rissanen's minimum description length (MDL) principle is presented as a restricted form of the descriptive complexity which avoids the uncomputability problem. We demonstrate the effectiveness of MDL through its application to AR processes. Lastly, we present and discuss LeClerc's application of MDL to the problem of image segmentation.
dc.description.commentsUniversity of Pennsylvania Department of Computer and Information Science Technical Report No. MS-CIS-91-08.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/7324
dc.legacy.articleid1413
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1413&context=cis_reports&unstamped=1
dc.source.issue399
dc.source.journalTechnical Reports (CIS)
dc.source.statuspublished
dc.titleDescriptive Complexity Approaches to Inductive Inference
dc.typeReport
digcom.contributor.authorAtteson, Kevin
digcom.identifiercis_reports/399
digcom.identifier.contextkey335903
digcom.identifier.submissionpathcis_reports/399
digcom.typereport
dspace.entity.typePublication
upenn.schoolDepartmentCenterTechnical Reports (CIS)
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
91_08.pdf
Size:
1.41 MB
Format:
Adobe Portable Document Format
Download
Collection
Reports