Feature transformation by function decomposition
IEEE Intelligent Systems and their ApplicationsPublished 1 March 1998
Blaž Zupan, Marko Bohanec, Janez Demšar, Ivan Bratko
Citations41
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The authors' function-decomposition method can discover and construct a hierarchy of new features that one can add to the original dataset or transform into a hierarchyof less complex datasets.
Abstract
The function decomposition described can identify subsets of existing features and discover nongiven functions that map these subsets to a new feature, also, it can organize the existing and new features into a hierarchy. The authors demonstrate their Hierarchy Induction Tool (HINT) system on a housing loan-allocation application. Methods for switching circuit design often implicitly deal with feature transformation. Such methods construct a circuit to implement a given or partially given tabulated Boolean function. The authors' function-decomposition method can discover and construct a hierarchy of new features that one can add to the original dataset or transform into a hierarchy of less complex datasets. The method allows the decomposition to deal with nominal-feature (that is, not necessarily binary) functions.
Keywords
Computer Science
C4.5: Programs for Machine Learning
23,665 Citations1992J. R. Quinlan
A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
Lecture notes in computer scienceEstimating attributes: Analysis and extensions of RELIEF
2,950 Citations1994Igor Kononenko
In the context of machine learning from examples this paper deals with the problem of estimating the quality of attributes with and without dependencies among them and is analysed and extended to deal with noisy, incomplete, and multi-class data sets.
IBM Journal of Research and DevelopmentSome Studies in Machine Learning Using the Game of Checkers. II—Recent Progress
690 Citations1967Arthur L. Samuel
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)ON THE DECOMPOSITION OF SWITCHING FUNCTIONS
280 Citations1961Sze-Tsen Hu
DEX: An Expert System Shell for Decision Support •
162 Citations1990Marko Bohanec
An approach to decision making that integrates multi-attribute techniques with expert systems is described, based on the explicit artic ulation of qualitative decision knowledge which is represented by a tree of attributes and dec ision rules.
Decomposition of multiple-valued functions
84 Citations2002Tadeusz Łuba
It is shown that the decomposition technique leads to additional compressing capabilities in PLA implementations, and another very promising area of application of decomposition is its effective representation of data in information systems, data bases and in other applications of information storing systems.
European Design Automation ConferenceA new approach to the decomposition of incompletely specified multi-output functions based on graph coloring and local transformations and its application to FPGA mapping
82 Citations1992Wei Wan, Marek Perkowski
IEEE Transactions on Systems Man and CyberneticsMultiattribute Decisionmaking Using a Fuzzy Heuristic Approach
77 Citations1979Janet Efstathiou, Vladislav Rajkovič
A fuzzy approach to DM is described, incorporating linguistic variables, relations, and algorithms, which helps to solve the problem of partial utilities and their interdependence.
Edinburgh Research Archive (University of Edinburgh)Inductive acquisition of expert knowledge
75 Citations1989Stephen Muggleton
An expert system shell is implemented, the Mugol environment, which facilitates knowledge acquisition by inductive inference and provides automatic explanation of run-time reasoning on demand and a new technique called sequence induction is investigated, which can be used in the construction of control systems.
VLSI designA General Approach to Boolean FunctionDecomposition and its Application in FPGABasedSynthesis
70 Citations1995Tadeusz Łuba, Henry Selvaraj
An effective logic synthesis procedure based on parallel and serial decomposition of a Boolean function and is suitable for different types of FPGAs including XILINX, ACTEL and ALGOTRONIX devices.
Machine Learning by Function Decomposition
62 Citations1997Blaž Zupan, Marko Bohanec +2 more
A new machine learning method is presented that, given a set of training examples, induces a definition of the target concept in terms of a hierarchy of intermediate concepts and their definitions, which effectively decomposes the problem into smaller, less complex problems.
Proceedings EURO-DAC '92: European Design Automation ConferenceA new approach to the decomposition of incompletely specified multi-output functions based on graph coloring and local transformations and its application to FPGA mapping
53 Citations2003Wei Wan, Marek Perkowski
Three methods are developed: fast graph coloring to perform a quasi-optimum 'don't care' assignment; variable partitioning to quickly find the 'best' partitions; and local transformation to transform a nondecomposable function into several decomposable ones.
Elsevier eBooksAUTOMATIC INDUCTION OF CLASSIFICATION RULES FOR A CHESS ENDGAME
48 Citations1982Alen David Shapiro, Timothy B. Niblett
Inductively derived decision rules which correctly classify all legal Black-to-move positions in the king and pawn versus king endgame are derived using a technique of ‘structured’ induction.
Journal of Computer and System SciencesLearning Boolean Read-Once Formulas over Generalized Bases
36 Citations1995Nader H. Bshouty, Thomas R. Hancock +1 more
Any basis class B meeting certain technical conditions can be extended to a polynomial time identification algorithm for read-once formulas over the union of B and the arbitrary functions of constant fan-in.
Lecture notes in computer scienceProblem decomposition and the learning of skills
33 Citations1995Donald Michie
One dimension of "divide and conquer" in problem solving concerns the domain and its subdomains and pre-occupation with free-standing performance has led to comparative neglect of this resource.
Functional decomposition of MVL functions using multi-valued decision diagrams
31 Citations2002Craig M. Files, Rolf Drechsler +1 more
The minimization of incompletely specified multi-valued functions using functional decomposition is discussed, based on expressing aMulti-valued function (learning problem) in terms of amulti-valued decision diagram that allows the use of Don't Cares.
IEEE Transactions on Systems Man and CyberneticsSignature Table Systems and Learning
25 Citations1982Alan W. Biermann, John Fairfield +1 more
A characterization theorem is given for the classes of functions which are representable by signature table systems and the usefulness of the theorem is demonstrated in the analysis and synthesis of such systems.
Machine LearningLearning from Examples and Membership Queries with Structured Determinations
20 Citations1998Prasad Tadepalli, Stuart Russell
Empirical results showing that when a tree-structured bias is available, the method significantly improves upon knowledge-free induction are presented and there are hard cryptographic limitations to generalizing these positive results to structured determinations in the form of a directed acyclic graph are presented.
Machine LearningLearning Nonoverlapping Perceptron Networks from Examples and Membership Queries
14 Citations1994Thomas R. Hancock, Mostefa Golea +1 more
A polynomial time algorithm is given that PAC learns any nonoverlapping perceptron network using examples and membership queries, and is able to identify both the architecture and the weight values necessary to represent the function to be learned.
Lecture notes in computer scienceConstructing intermediate concepts by decomposition of real functions
14 Citations1997Janez Demšar, Blaž Zupan +2 more
A technique for discovering useful intermediate concepts when both the class and the attributes are real-valued, based on a decomposition method originally developed for the design of switching circuits and recently extended to handle incompletely specified multi-valued functions.
A management decision support system for allocating housing loans
11 Citations1996Marko Bohanec, Bojan Cestnik +1 more
A system for supporting management decisions in the allocation of housing loans is presented, based on a knowledge base that contains several qualitative and quantitative decision models, and is combined with a database.
Pattern theoretic knowledge discovery
9 Citations2002Jeffery A. Goldman
A new approach to learning demonstrates a powerful method for finding patterns in a robust manner and explores the current limitations of a pattern theoretic approach as applied to the general KDD problem.