On the number of multilinear partitions and the computing capacity of multiple-valued multiple-threshold perceptrons

We introduce the concept of multilinear partition of a point set V/spl sub/R/sup n/ and the concept of multilinear separability of a function f:V/spl rarr/K={0, ..., k-1}. Based on well known relationships between linear partitions and minimal pairs, we derive formulae for the number of multilinear partitions of a point set in general position and of the set K/sup 2/. The (n, k, s)-perceptrons partition the input space V into s+1 regions with s parallel hyperplanes. We obtain results on the capacity of a single (n, k, s)-perceptron, respectively for V/spl sub/R/sup n/ in general position and for V=K/sup 2/. Finally, we describe a fast polynomial-time algorithm for counting the multilinear partitions of K/sup 2/.

[1]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[2]  Sverrir Olafsson,et al.  The Capacity of Multilevel Threshold Functions , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[4]  T. Kailath,et al.  Discrete Neural Computation: A Theoretical Foundation , 1995 .

[5]  Zvonko G. Vranesic,et al.  Synthesis of Multivalued Multithreshold Functions for CCD Implementation , 1986, IEEE Transactions on Computers.

[6]  Ivan Stojmenovic,et al.  STRIP - a strip-based neural-network growth algorithm for learning multiple-valued functions , 2001, IEEE Trans. Neural Networks.

[7]  Ivan Stojmenovic,et al.  Synthesis of multiple-valued logic functions by neural networks , 1998 .

[8]  Zoran Obradovic,et al.  Learning with Discrete Multi-valued Neurons , 1990, J. Comput. Syst. Sci..

[9]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[10]  Jovisa D. Zunic,et al.  On the Number of Linear Partitions of the (m, n)-Grid , 1991, Inf. Process. Lett..

[11]  Zoran Obradovic,et al.  Computing with Discrete Multi-Valued Neurons , 1992, J. Comput. Syst. Sci..

[12]  Thomas M. Cover,et al.  Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..

[13]  Alfred M. Bruckstein,et al.  The number of digital straight lines on an N×N grid , 1990, IEEE Trans. Inf. Theory.

[14]  Nils J. Nilsson,et al.  Learning Machines: Foundations of Trainable Pattern-Classifying Systems , 1965 .

[15]  Ryuzo Takiyama,et al.  The Separating Capacity of a Multithreshold Threshold Element , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Donald R. Haring,et al.  Multi-threshold threshold elements , 1966, IEEE Trans. Electron. Comput..

[17]  E. Wright,et al.  An Introduction to the Theory of Numbers , 1939 .