This chapter outlines the research, development and perspectives of quantum neural networks – a burgeoning new field which integrates classical neurocomputing with quantum computation [1]. It is argued that the study of quantum neural networks may give us both new undestanding of brain function as well as unprecedented possibilities in creating new systems for information processing, including ...

In this paper, global exponential stability in Lagrange sense for periodic neural networks with various activation functions is further studied. By constructing appropriate Lyapunov-like functions, we provide easily verifiable criteria for the boundedness and global exponential attractivity of periodic neural networks. These theoretical analysis can narrow the search field of optimization compu...

The learning phenomenon allows various analysis levels, but this article treats one specific paradigm of Artificial Intelligence, Artificial Neural Networks, whose main virtue is their capacity to look for unified and mutually satisfactory solutions with an important turn towards biological and psychological models. Given the fact that a substantial part of the procedures, methods, etc. propose...

Models of associative memory usually have full connectivity or if diluted, random symmetric connectivity. In contrast, biological neural systems have predominantly local, non-symmetric connectivity. Here we investigate sparse networks of threshold units, trained with the perceptron learning rule. The units are given position and are arranged in a ring. The connectivity graph varies between bein...

Some contributions of physics towards the understanding of consciousness are described. As recent relevant models, associative memory neural networks are mentioned. It is shown that consciousness and quantum physics share some properties. Two existing quantum models are discussed.

In the Artificial Intelligence field, two areas have attracted a lot of attention in the past years: Artificial Neural Networks (ANN’s) and Genetic Algorithms (GA). The artificial neural networks, by their capacity to learn non-linear relationships between an input and an output space have a lot of applications: modeling and controlling dynamic processes and systems, signal processing, pattern ...

In this paper, we introduce an associative memory storing grey scale images. It’s based on a suitable translation of the grey scale image into a Gray-coded binary image, stored in a single BSB binary neural network. The particular BSB we are going to exploit has the property of local connectivity. The chosen learning algorithm guarantees asymptotic stability of the stored patterns, low computat...

The conventional synthesis procedure of discrete time sparsely interconnected neural networks (DTSINNs) for associative memories may generate the cells with only selffeedback due to the sparsely interconnected structure. Although this problem is solved by increasing the number of interconnections, hardware implementation becomes very difficult. In this letter, we propose the DTSINN system which...