The performance of symbolic inference tasks has long been a challenge to connectionists. In
this paper, we present an extended survey of this area. Existing connectionist inference …

Article Page 1 Article Connectionist variable binding Antony Browne1 and Ron Sun2 (1) School
of Computing, Information Systems and Mathematics, London Guildhall University, London …

Two methods of obtaining structured information from a trained feed-forward neural network
are discussed. The first of these methods extracts structured representations from the hidden …

The performance of symbolic inference tasks has long been a challenge to connectionists. In
this paper, we present an extended survey of this area. Existing connectionist inference …

It has been pointed out many times that for all of the good properties of neural networks, until
they can explain what they are doing they cannot be used in some systems, for example …

This special issue of the journal is devoted wholly to the topic of symbol processing in
connectionist systems. As far as intelligent systems are concerned, symbols can be …