Quantum arti®cial neural network architectures and components Ajit Narayanan * , Tammy Menneer School of Engineering and Computer Science, Old Library, University of Exeter, Exeter EX4 4PT, UK Received 8 October 1999; accepted 4 July 2000 Abstract It is shown by classical simulation and experimentation that quantum arti®cial neural networks (QUANNs) are more ecient and in some cases more powerful than classical arti®cial neural networks (CLANNs) for a variety of experimental tasks. This eect is particularly noticeable with larger and more complex domains. The gain in eciency is achieved with no generalisation loss in most cases. QUANNs are also more powerful than CLANNs, again for some of the tasks examined, in terms of what the network can learn. What is more, it appears that not all components of a QUANN architecture need to to be quantum for these advantages to surface. It is demonstrated that a fully quantum neural network has no advantage over a partly quantum network and may in fact produce worse results. Overall, this work provides a ®rst insight into the expected behaviour of individual components of QUANNs, if and when quantum hardware is ever built, and raises questions about the interface between quantum and classical components of future QUANNs. Ó 2000 Elsevier Science Inc. All rights reserved. 1. Background to quantum neural networks As yet, there is little understanding of the essential components of arti®cial neural networks (ANNs) based on quantum theoretical concepts and Information Sciences 128 (2000) 231±255 www.elsevier.com/locate/ins * Corresponding author. E-mail addresses: a.narayanan@ex.ac.uk (A. Narayanan), tammy@spikeisland.freeserve.co.uk (T. Menneer). 0020-0255/00/$ - see front matter Ó 2000 Elsevier Science Inc. All rights reserved. PII: S 0 0 2 0 - 0 2 5 5 ( 0 0 ) 0 0 0 5 5 - 4