Concept learning
The minimum description length principle is a formalization of Occam's Razor in which the best hypothesis for a given set of data is the one that leads to the largest compression of the data. In short, data that shows a lot of regularities and/or patterns, may be compressed without losing any important information. Applying this to learning, we can conclude that the more regularity and/or patterns we are able to find within data, the more we have learned about the data.
To illustrate this imagine the following as representations of two sets of data:
Set 1: 100110111011011001010110110010001100101101 Set 2: 011011011011011011011011011011011011011
Set 1 appears as to be random, but we with set 2 we are able to detect a pattern, thereby allowing us to describe it as "011 repeating 13 times.
For more information see: http://learningtheory.org/articles/mdlintro.pdf
[
See also
[
Footnotes
- Note 1: http://portal.acm.org/citation.cfm?id=66445
- Note 2: Dejong, Gerald and Raymond Mooney. "Explanation-based Learning: An Alternative View." Machine Learning. Volume 1. 1986. pp. 145-176.
- Note 3: See 1.
- Note 4: Ashcraft, Mark A. Cognition.Fourth Edition. Pearson Eduction, Inc: Upper Saddle River, NJ. 2006.
- Note 5: See 2.
- Note 6: http://dictionary.reference.com/browse/analogy
[
References
- ^ http://en.wikipedia.org/wiki/ACT-R
- ^ MIT : Brain and Cognitive Sciences : People : Faculty : Joshua Tenenbaum
- Ratcliff, Roger (2006). "Comparing Exemplar and Rule-Based Theories of Categorization". Current Directions in Psychological Science 15: 9–13. doi:.
- A Rational Analysis of Rule-based Concept Learning. Retrieved on 2007-12-04.
- GA-based Rule Enhancement in Concept Learning. Retrieved on 2007-12-04.
- Bruner, J., Goodnow, J. J., & Austin, G. A. (1967). A study of thinking. New York: Science Editions.
- Feldman, Jacob (2003). "The Simplicity Principle in Human Concept Learning". Psychology Science 12: 227–232.
- Rendell, Larry (1986). "A general framework for induction and a study of selective induction". Machine Learning 1: 177–226. doi:.
- Watanabe, Satosi (1969). Knowing and Guessing: A Quantitative Study of Inference and Information. New York: Wiley.
- Watanabe, Satosi (1985). Pattern Recognition: Human and Mechanical. New York: Wiley.
- Solomonoff, R. J. (1964). "A formal theory of inductive inference. Part I". Information and Control 7 (1): 1–22. doi:.
- Solomonoff, R. J. (1964). "A formal theory of inductive inference. Part II". Information and Control 7 (2): 224–254. doi:.
- ACT-R. Retrieved on 2007-12-04.
- Brain and Cognitive Sciences. Massachusetts Institute of Technology. Retrieved on 2007-11-23.
- Kearsley, Greg (Copyright 1994-2007). Component Display Theory (M.D. Merrill). Retrieved on 2007-12-04.
- Kearsley, Greg (Copyright 1994-2007). Concept. Retrieved on 2007-12-04.
- Component Display Theory (2007-04-10). Retrieved on 2007-12-04.
- Concept Attainment (Copyright 1999). Retrieved on 2007-12-04.
- Concept Learning (2007-11-7). Retrieved on 2007-12-04.
- Concept Formation. The McGraw-Hill Companies (Copyright 2007). Retrieved on 2007-12-04.
- 6Berry, Donald A. (1997-1998). "Teaching Elementary Bayesian Statistics with Real Applications in Science". The American Statistician 5 (3): 241–246.
- 7Brown, Harold I. (1994). "Reason, Judgment and Bayes's Law". Philosophy of Science 61 (3): 351–369. doi:.
- 5Lindley, Dennis V. (1983). "Theory and Practice of Bayesian Statistics". The Statistician 32 (1/2): 1–11. doi:.
For more information review our copyright contact and privacy policy.
