Learn More
The Set Covering problem (SCP) is a well known combinatorial optimization problem, which is NP-hard. We conducted a comparative study of eight diierent approximation algorithms for the SCP, including several greedy variants , fractional relaxations, randomized algorithms and a neural network algorithm. The algorithms were tested on a set of random-generated(More)
Recently, there has been considerable interest in deriving and applying knowledge-based, empirical potential functions for proteins. These empirical potentials have been derived from the statistics of interacting, spatially neighboring residues, as may be obtained from databases of known protein crystal structures. In this paper we employ neural networks to(More)
A neural network model, the INN (Inverted Neurons Network), is applied to the Maximum Clique problem. First, I describe the INN model and how it implements a given graph instance. The model has a threshold parameter t, which determines the character of the network stable states. As shown in an earlier work 5], the stable states of the network correspond to(More)
A new learning algorithm, learning by choice of int ern al repr esentations (CHIR), was recently int roduc ed. Th e basic version of thi s algorit hs was developed for a two-layer, single-out put , feed-forward network of binary neurons. This paper presents a gener alized version of t he CHIR algorithm th at is capable of t raining mult iple-output net(More)
A new learning algorithm for feedforward network s, learn-in g by choice of in t ern al rep resent at ions (C HIR), was recently introduced [1,2]. W hereas man y algor it hm s red uce th e learning proce ss to minimizin g a cost fu nction over t he weights, our method treats th e internal representations as t he funda me nt al ent it ies to b e determi ned.(More)
We study the extent to which xing the second layer weights reduces the capacity and generalization ability of a two-layer perceptron. Architectures with N inputs, K hidden units and a single output are considered, with both overlapping and non-overlapping receptive elds. We obtain from simulations one measure of the strength of a network-its critical(More)