Neural models of cursive script handwriting

The main characteristics of cursive script handwriting are reviewed, and a basic coding scheme is described. Two types of neural networks are described: (i) a self-organizing network, similar to that used by T. Kohonen for his phonetic typewriter (see IEEE Comput., p.11-22, 1988), which is able to discover Graphotopic Maps; (ii) a three-layer perceptron called NetWrite in analogy with the NeTalk architecture developed by C.R. Rosemberg and T. Sejnowksi (see Complex Syst., vol.1, p.145-68, 1987), that can recognize digraphs. Pros and cons are discussed, as well as an integration proposal.<
>