AUTOMATIC SETTING OF ARTICLE FORMAT THROUGH NEURAL NETWORKS

The automatic format setting of journal articles for reducing the work load of computer users involves two processes: automatic acquisition o f article format and automatic recall of article format. Several neura l networks have been explored to implement the two processes. The adva ntages and disadvantages of these neural networks are evaluated in com parison with capabilities of conventional computer programs. A heteroa ssociative back-propagation network has been developed for the automat ic acquisition process. This network excels over computer programs bec ause of its abilities in learning and generalizing implicit knowledge from examples. A bidirectional associative memory network, a Boltzman network, and an autoassociative back-propagation network have been inv estigated for the automatic recall process. None of them excel over co mputer programs in terms of recall accuracy.