Open Access
Threshold networks for pattern classification
Martin Anthony
- 01 Jan 2008
TL;DR: This paper describes a method of constructing one-hidden layer feedforward linear threshold networks to represent Boolean functions (or partially-defined Boolean functions) and compares this approach to the standard approach based on a Boolean function’s disjunctive normal form and to other approaches based on sequential linear separation.
read more
Abstract: This paper describes a method of constructing one-hidden layer feedforward linear threshold networks to represent Boolean functions (or partially-defined Boolean functions). The first step in the construction is sequential linear separation, a technique that has been used by a number of researchers [7, 11, 2]. Next, from a suitable sequence of linear separations, a threshold network is formed. The method described here results in a threshold network with one hidden layer. We compare this approach to the standard approach based on a Boolean function’s disjunctive normal form and to other approaches based on sequential linear separation [7, 11].
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Journal Article
On the computational power of boolean decision lists
TL;DR: The computational power of decision lists over AND-functions versus threshold-?
17
References
Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition
TL;DR: It is shown that a family of surfaces having d degrees of freedom has a natural separating capacity of 2d pattern vectors, thus extending and unifying results of Winder and others on the pattern-separating capacity of hyperplanes.
2.3K
•Book
Discrete Neural Computation: A Theoretical Foundation
Kai-Yeung Siu,Vwani P. Roychowdhury,Thomas Kailath +2 more
- 01 Jan 1995
TL;DR: 1. Computing Symmetric Functions 2. Depth Efficient Arithmetic Circuits 3. Rational Approximation and Optimal Size Circuits.
164
A Convergence Theorem for Sequential Learning in Two-Layer Perceptrons
TL;DR: It is proved that the internal representations obtained by such procedures are linearly separable and compare favourably with results of other growth algorithms.
Threshold Numbers and Threshold Completions
TL;DR: The threshold number t(f) of a positive Boolean function f(x1, …, xn) is the least number of linear inequalities whose solution set in 0-1 variables is the set of zeros of f.
60
On learning simple neural concepts: from halfspace intersections to neural decision lists
Mario Marchand,Mostefa Golea +1 more
TL;DR: It is shown how the greedy method can be generalized to handle this class of concepts, the class of halfspace intersections, which shows that these concepts are not only important from the theoretical point of view, but also in practice.