Compact Rulesets from XCSI
نویسنده
چکیده
An algorithm is presented for reducing the size of evolved classiier populations. On the Wisconsin Breast Cancer dataset, the algorithm produced compact rulesets substantially smaller than the populations , yet performance in cross-validation tests was nearly unchanged. Classiiers of the rulesets expressed readily interpretable knowledge about the dataset that should be useful to practitioners.
منابع مشابه
Data Mining using Learning Classifier Systems
[118] Stewart W. Wilson. Compact Rulesets from XCSI. In Lanzi et al. [73], pages 196–208.[119] Ian H. Witten and Eibe Frank. Data Mining: practical machine learning tools and techniques with java implementations. Morgan Kaufmann, 2000. [120] G. Zweiger. Knowledge discovery in gene-expression-microarray data: mining theinformation output of the genome. Trends in Biotechnology, 17:429...
متن کاملRule Induction as Exploratory Data Analysis
This paper examines induction decision rule for the purpose of exploratory data analysis, and presents various tools and techniques for this. Decision tables provide a compact, consistent format that allows several fairly large classiiers to be examined on a page. Variation in rulesets arises naturally to a surprisingly large degree from small diierences in sampling from a training set, and ext...
متن کاملA Simple , Fast , and E ective Rule
We describe SLIPPER, a new rule learner that generates rulesets by repeatedly boosting a simple, greedy, rule-builder. Like the rulesets built by other rule learners , the ensemble of rules created by SLIPPER is compact and comprehensible. This is made possible by imposing appropriate constraints on the rule-builder, and by use of a recently-proposed generalization of Ad-aboost called conndence...
متن کاملA Simple, Fast, and Effictive Rule Learner
We describe SLIPPER~ a new rule learner that generates rulesets by repeatedly boosting a simple, greedy, rule-builder. Like the rulesets built by other rule learners, the ensemble of rules created by SLIPPER is compact and comprehensible. This is made possible by imposing appropriate constraints on the rule-builder, and by use of a recently-proposed generalization of Adaboost called confidence-...
متن کاملGames from Basic Data Structures
In this paper, we consider combinatorial game rulesets based on data structures normally covered in an undergraduate Computer Science Data Structures course: arrays, stacks, queues, priority queues, sets, linked lists, and binary trees. We describe many rulesets as well as computational and mathematical properties about them. Two of the rulesets, Tower Nim and Myopic Col, are new. We show polyn...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001