Pattern Recognition: Human and Mechanical

By Satosi Watanabe. 1985

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): “…1989; Palm, 1992; Pearlmutter &Hinton, 1986; Ritter & Kohonen, 1989; Rubner & Schulten, 1990; Sanger, 1989; Saund, 1994; von der Malsburg, 1973; Watanabe, 1985; Willshaw & von der Malsburg, 1976); see also post-2000 work (e.g., Carreira-Perpinan, 2001; Franzius, Sprekeler, & Wiskott, 2007;…”
Pattern classification with missing data: a review (2010, background): “In general [4], a classical definition of pattern is an entity that can be represented by a set of properties and variables (feature vector).”
Data clustering: a review (1999, background): “Watanabe’s theorem of the ugly duckling [Watanabe 1985] states:”
Finding Minimum Entropy Codes (1989, methodology): “The general idea of Minimum Entropy Coding has been discussed by Watanabe (1981, 1985) and the principle is described in a previous article (Barlow 1989); the aim is to find a set of symbols to represent the messages such that, in the normal environment, the occurrence of each symbol is independen”
Statistical Pattern Recognition: A Review (2000, background): “Watanabe [163] defines a pattern ªas opposite of a chaos; it is an entity, vaguely defined, that could be given a name.º For example, a pattern could be a fingerprint image, a handwritten cursive word, a human face, or a speech signal.”
Writeprints: A stylometric approach to identity-level identification and similarity detection in cyberspace (2008, methodology): “K-L transforms are a PCA variant often used in pattern recognition studies [Watanbe 1985; Webb 2002] and provide a mechanism for using multiple individual-authorlevel feature sets.”
A Bayesian framework for concept learning (1999, background): “Not only are priors empirically real, they are in principle necessary for any kind of inductive inference to succeed (Goodman, 1955; Watanabe, 1985; Mitchell, 1980); recall my argument above that all powers of two except 32 would be a better explanation of the observed examples 16, 8, 2, and 64 than”
Feature Extraction Through LOCOCODE (1999, unknown): “Some COCOFs explicitly favor near-factorial, minimally redundant codes of the input data (see, e.g., Watanabe, 1985; Barlow, Kaushal, & Mitchison, 1989; Linsker, 1988; Schmidhuber, 1992; Schmidhuber & Prelinger, 1993; Schraudolph & Sejnowski, 1993; Redlich, 1993; Deco & Parra, 1994).”
Incremental Induction of Decision Trees (1989, background): “See Watanabe [1985] for a historical perspective on applying the notion of physical entropy to information”
Could information theory provide an ecological theory of sensory processing? (2011, background): “A third possible explanation for why a sensory pathway might choose to preprocess incoming signals to improve their efficiency is that efficiency might facilitate the pattern recognition process (see also Barlow 1985; Watanabe 1981, 1985).”
Data Clustering (2008, unknown): “Watanabe's theorem of the ugly duckling [192] states: Insofar as we use a nite set of predicates that are capable of distinguishing any two objects considered, the number of predicates shared by any two such objects is constant, independent of the choice of objects.”
Akaike's Information Criterion and Recent Developments in Information Complexity. (2000, background): “If we wish to extract fewer and more important variables, it will be desirable that they be statistically independent, because the presence of interdependence means redundancy and mutual duplication of information contained in these variables (Watanabe, 1985).”
Peripheral vision and pattern recognition: a review. (2011, methodology): “We prefer an approach to pattern recognition that is based on a more general concept than template matching and assumes that stimuli are sorted and given meaning by assigning them to learned categories (Bruner, Goodnow, & Austin, 1956, Bruner, 1957; Watanabe, 1985).”
Object detection using feature subset selection (2004, methodology): “We have tested the proposed framework on two challenging applications: vehicle detection and face detection.”
Consistency-based search in feature selection (2003, background): “Informationtheoretic considerations [45] suggested something similar: using a good feature of discrimination provides compact descriptions of each class, and these descriptions are maximally distinct.”
Information Theoretic Clustering (2002, methodology): “Information theory [47], [48] was used in clustering by Watanabe [50] and by many other researchers [8], [22], [49].”