Goto

Collaborating Authors

 network generalization

Network generalization for production: Learning and producing styled letterforms

Neural Information Processing Systems

We designed and trained a connectionist network to generate letterfonns in a new font given just a few exemplars from that font. It was necessary to have separate but interconnected hidden units for " letter" and "font" representations - several alternative architectures were not successful.

Network generalization for production: Learning and producing styled letterforms

Neural Information Processing Systems

We designed and trained a connectionist network to generate letterfonns in a new font given just a few exemplars from that font.

Network generalization for production: Learning and producing styled letterforms

Neural Information Processing Systems

Here during the production event a very low infonnational input ("Madonna," and "Matisse") is used