Stochastic Complexity in Statistical Inquiry

Rissanen, Jorma

doi:10.1142/0822

Cited by 947 publications

(956 citation statements)

References 0 publications

Supporting

Mentioning

940

Contrasting

Unclassified

Order By: Relevance

“…A second result is that the shortest code can be used for prediction, with a high probability of 'convergence' on largely correct predictions. Finally, a third powerful line of justification for simplicity as an effective method of induction is its widespread use in machine learning [8,9] and statistics [10].…”

Section: Quantifying Simplicitymentioning

confidence: 99%

“…The answer is that the projection is much more stable for the perpendicular ellipse; for the highly skewed ellipse the angle of orientation must be specified more precisely, costing additional code length, to obtain an equally good fit with the data. [10] Formal measures of simplicity [37,38] a Many pattern-finding problems have been successfully approached by mathematicians and computer scientists using a simplicity principle. In many of these areas, the simplicity principle has also been used as a starting point for modelling cognition.…”

Section: Box 1 Empirical Datamentioning

confidence: 99%

See 1 more Smart Citation

Simplicity: a unifying principle in cognitive science?

Chater

Vitányi

2003

Trends in Cognitive Sciences

349

282

View full text Add to dashboard Cite

Section: Quantifying Simplicitymentioning

confidence: 99%

Section: Box 1 Empirical Datamentioning

confidence: 99%

Simplicity: a unifying principle in cognitive science?

Chater

Vitányi

2003

Trends in Cognitive Sciences

349

282

View full text Add to dashboard Cite

“…In the process of acquiring a vocabulary, infants would be well advised to avoid any temptation to consider consonants, or consonant clusters, as potential words to be added to the lexicon. Brent and Cartwright (1996) conducted a series of computational studies of vocabulary acquisition, in which they used a Minimum Representation Length (Rissanen, 1989) tech nique to learn a vocabulary from selections of the CHILDES database (Mac-markings were deleted. Brent and Cartwright showed that vocabulary acquisi tion was improved by adopting a strategy which insisted that all words con tained a vowel, thus effectively ruling out consonants as feasible candidate words.…”

Section: Ruling Out Impossible Segmentationsmentioning

confidence: 99%

The Possible-Word Constraint in the Segmentation of Continuous Speech

Norris

McQueen

Cutler

et al. 1997

Cognitive Psychology

225

280

View full text Add to dashboard Cite

We propose that word recognition in continuous speech is subject to constraints on what may constitute a viable word of the language. This Possible-Word Constraint (PWC) reduces activation of candidate words if their recognition would imply word status for adjacent input which coultl not be a word -for instance, a single consonant. In two word-spotting experiments, listeners found it much harder to detect apple, for example, in fapple (where [f] alone would be an impossible word), than in vujfapple (where vuff could be a word of English). We demonstrate that the PWC can readily be implemented in a competition-based model of continuous speech recognition, as a constraint on the process of competition between candidate words; where a stretch of speech between a candidate word and a (known or likely) word boundary is not a possible word, activation of the candidate word is reduced. This implementation accu rately simulates both the present results and data from a range of earlier studies of speech segmentation. © 1997 Academic Press INTRODUCTIONWhen we listen to continuous speech, we apprehend a sequence of discrete words. The effortlessness with which we understand speech might suggest that recognition of spoken words is a rather simple task; but in fact it is a complex process, in which a very variable and largely continuous speech signal has to be mapped onto a lexicon of tens of thousands of words. TheWe thank the Longman Group, U.K. Inc. for allowing us to use a machine-readable version of the Longman Dictionary o f Contemporary English (Procter, 1975 Owned by Academic Press, 525 B Street, Suite 1900, San Diego, CA 92101-4495 Known bondholders, mortgagees, and other security holders owning or holding 1 percent or more of total amount o f bonds, mortgages, and other securities None Paragraphs 2 and 3 include, in cases where the stockholder or security holder appears upon the books o f the company as trustee or in any other fiduciary relation, the name o f the person or corporation for whom such trustee is acting, also the statements in the two paragraphs show the affiant's full knowledge and belief as to the circumstances and conditions under which stockholders and security holders who do not appear upon the books o f the company as trustees, hold stock and securities in a capacity other than that o f a bona fide owner Names and addresses of individuals who are stockholders o f a corporation which itself is a stockholder or holder of bonds, mortgages, or other securities of the publishing corporation have been included in paragraphs 2 and 3 when the interests o f such individuals are equivalent to I percent or more of the total amount of the stock or securities of the publishing corporation Total no copies printed average no copies each issue during preceding 12 months 2249, single issue nearest to filing date 2247 Paid circulation (a) to term subscribers by mail, carrier delivery, or by other means average no copies each issue during preceding 12 months 1054, single issue nearest to filing date 1050 (b) Sal...

show abstract

“…in a setting where only the data received are of interest. In Rissanen's principle of Minimum Description Length ( [17]), the criterion is the efficiency of the representation of a given data set. This again has two components, one being the complexity of the model that represents the data, or the length of the program needed to describe the model, the other one being the length of the representation of the data by the model.…”

Section: Learningmentioning

confidence: 99%

“…In principle, this quantification is also possible through other means, for example through the length of the representation of the data in the internal code of the system. If we assume optimal coding, however, which is a consequence of the minimization of internal complexity, then the length of the representation of a datum X i (θ) behaves like log 2 P (X i (θ)) (a code is good if frequent inputs are represented by short code words, see [17]). How external complexity can be increased then depends on the time scale involved.…”

Section: Introduction: Complex Adaptive Systemsmentioning

confidence: 99%