Watanabe's Theorem of the Ugly Duckling

This entire post is quotes from Kanal (1993)

Theorem of the Ugly Duckling
(by Watanabe)
If the resemblance or similarity between two objects is measured by the maximum number of predicates shared by them, then the similarity between any pair of arbitrary objects is the same. Thus a swan and a duck, and two swans are equally similar. This situation arises because all predicates are treated equally.
...performing logical manipulation on raw data resulting from observation does not provide grouping among observed objects because unless some predicates are considered more important than others, i.e., weighted more heavily, the above theorem holds.

What makes human cognition possible is the evaluative weighing whose origin is aesthetic and emotional in the broadest sense of the terms.

In Pattern Recognition - Human and Mechanical he summarizes earlier papers of his that cover a variety of philosophical views on categorisation, from Greeks and Western philosophers to Brahmanism and Buddhism.

many of the points about categorisation touched on in Wantabe's papers and books are addressed at length in an excellent book by George Lakoff called Women, Fire and Dangerous Things (see)

Quotes on Modeling Techniques from Kanal

interesting quotes from Kanal (1993)
1. Paul Werbos had talked about error back propagation in his doctoral thesis "Beyond regression: new tools for prediction and analysis in behavioral sciences" (1974) before Rumelhart et al (1986).

2.

A basic problem of statistical pattern recognition, viz., the dimensionality -sample size problem also arises in artificial neural systems. In the design of multilayer feedforward networks one question is how many hidden units to use.

A few techniques are reviewed - but they appear an over-kill (in the best case) and clearly inapplicable (in the worst case) because in my experiments the size is not crucial - the order of free parameters in the network remains constant. there is only one hidden layer - and no. of hidden units are of order of 1 to 10.

3.

While the generation of artificial neural networks excite us, we should keep in mind that:

(1) As has been shown by [Comparing hierarchical statistical classifiers with error back propagation neural network; Kanal et al (1989)], often fairly simple statistical decision tree methods give equivalent or better results;

(2) the various neural network paradigms for pattern classification introduced in recent years have close connections with stochastic approximation, estimation and classification procedures known in statistical pattern recognition; and

(3) rather good algorithms have been developed in recent years for large combinatorial optimization problems whereas neural networks have so far only been demonstrated on much smaller problems. It remains to be shown that combinatorial optimization is a good area for artificial neural networks.

4.

...the problem of scalability remains one of the basic concerns for employing various pattern recognition, parallel processing, and machine intelligence tools on real world problems.

5. "They were AI as long as it was unclear how to make them work." After a very interesting discussion on what is AI, based on AI Magazine, Roger Shank (1991)

6. Theorem of the Ugly Duckling
(by Watanabe)
separate post.

Pattern Recognition - review paper 1992

On pattern, categories and alternate realities
Laveen N Kanal
Pattern Recognition letters 14 (1993) 241 - 255

A review on pattern recognition presented at the 11th international conference of pattern recognition on reception of an award; the author is from dept of computer science.

The review having been presented in 1992 is, now, dated. The good thing is that certain questions are so fundamental that they cannot be dated. Some of such questions are presented in an informal language, which makes it very good. Tho there is some history also described - it is so intertwined with the personal history of the author that apart from giving an interesting perspective, it does little else. The quotes (also picked from general philosophy) are excellent and i have posted them separately.

Finally an excellent read for anyone interested in pattern recognition or one of the techniques used for them.