An Information Measure for Classification

By Chris S. Wallace, D. Boulton. 1968

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “…of a solution candidate by the length of the shortest program that computes it (e.g., Blumer, Ehrenfeucht, Haussler, & Warmuth, 1987; Chaitin, 1966; Grünwald,Myung, & Pitt, 2005; Kolmogorov, 1965b; Levin, 1973a; Li & Vitányi, 1997; Rissanen, 1986; Solomonoff, 1964, 1978;Wallace & Boulton, 1968).”
Community detection in graphs (2009, methodology): “There is no clear-cut recipe to select a model, but a bunch of heuristics, like Akaike Information Criterion (AIC) [310], Bayesian Information Criterion (BIC) [311], Minimum Description Length (MDL) [312,313], MinimumMessage Length (MML) [314], etc.”
Learning Deep Architectures for AI (2007, background): “Minimum Description Length (Rissanen, 1990) and its variants such as Minimum Message Length (Wallace & Boulton, 1968) also usethis principle in the context of random variables with many realizations: a good predictive model (in terms of out-of-sample log-likelihood) is also one that can assign a sho”
Learning Bayesian networks: approaches and issues (2011, background): “4.7.3 Minimum message length A newer scoring criterion for Bayesian networks, based on the work of Wallace and Boulton (1968), is one that computes the MML of a structure, its parameters and data (Wallace et al., 1996).”
Comparing dynamic causal models (2004, methodology): “This is the rationale behind the Minimum Description Length (MDL) model comparison criterion (Wallace and Boulton, 1968).”
Model Selection Techniques: An Overview (2018, background): “The minimum message length (MML) principle [29] was proposed from an information-theoretic perspective.”
Dynamic clustering using particle swarm optimization with application in image segmentation (2006, background): “measure [also known as the minimum message length (MML)] [39, 40] is calculated and based on this calculation the assignment is accepted or rejected.”
Model Selection and the Principle of Minimum Description Length (2001, methodology): “Originally designed for cluster analysis, their principle of Minimum Message Length (MML) also appeals to a notion of code length to strike a balance between model complexity and ﬁdelity to the data.”
MML clustering of multi-state, Poisson, von Mises circular and Gaussian distributions (2000, methodology): “The ﬁrst Snob program (since out-dated) (Wallace and Boulton 1968) was possibly one of the ﬁrst programs for Gaussian mixture modelling, although many statistical and machine learning approaches to this problem have been developed since (e.g., McLachlan et al .”