Of the many types of neural networks that have recently emerged this paper reviews
weightless neuron models. Some advantages of this model are:(1) systems may be built …

Given dissimilarity data on pairs of objects in a set, we study the problem of fitting a tree
metric to this data so as to minimize additive error (ie some measure of the difference …

A novel way to simulate Turing Machines (TMs) by Artificial Neural Networks (ANNs) is
proposed. We claim that the proposed simulation is in agreement with the correct …

Automata and Weightless Neural Networks 13.89 Page 1 247 Automata and Weightless Neural
Networks Teresa B. Ludermir" Wilson R. de Oliveirat Departamento de Informática …

It is well known that, in a broad sense, recurrent neural networks are equivalent to Turing
machines. However, in general, such computational power has not been achieved by the …

Motivated by our earlier work on Turing computability via neural networks (1992, 2001) and
the results by Maass et al.(1997, 1998) on the limit of what can be actually computed by …

We propose a way to simulate Turing machines (TMs) by neural networks (NNs) which is in
agreement with the correct interpretation of Turing's analysis of computation; compatible with …

A fundamental question in the field of artificial neural networks is what set of problems a
given class of networks can perform (computability). Such a problem can be made less …

An algorithm to insert a priori knowledge in a neural network is described. This algorithm not
only guarantees the construction of a neural network which implements a described …

Most neural networks models are similar in computation power. They are equivalent to finite
state automata. These models become equivalent to Turing machines if a infinite number of …