The Capacity of Multilevel Threshold Functions

Authors:
S. 'Olafsson;Y. S. Abu-Mostafa
Affiliations:
California Institute of Technology, Pasadena;California Institute of Technology, Pasadena
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1988

Citing 1
Cited 8

Comments on Takiyama's Analysis of the Multithreshold Threshold Element

IEEE Transactions on Pattern Analysis and Machine Intelligence

The Computing Capacity of Three-Input Multiple-Valued One-Threshold Perceptrons

Neural Processing Letters
Design of Supervised Classifiers Using Boolean Neural Networks

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Partitions Encoding

Digital and Image Geometry, Advanced Lectures [based on a winter school held at Dagstuhl Castle, Germany in December 2000]
Digital partitions encoding

Digital and image geometry
Generalization Error Bounds for Threshold Decision Lists

The Journal of Machine Learning Research
On data classification by iterative linear partitioning

Discrete Applied Mathematics - Discrete mathematics & data mining (DM & DM)
On data classification by iterative linear partitioning

Discrete Applied Mathematics
Fast and efficient colour inspection using sets of ellipsoidal regions

Machine Graphics & Vision International Journal

Quantified Score

Hi-index	0.14

Visualization

Abstract

Lower and upper bounds for the capacity of multilevel threshold elements are estimated, using two essentially different enumeration techniques. It is demonstrated that the exact number of multilevel threshold functions depends strongly on the relative topology of the input set. The results correct a previously published estimate and indicate that adding threshold levels enhances the capacity more than adding variables.