Showing papers on "Handwriting recognition published in 1965"
43 citations
29 citations
TL;DR: Alearning program incorporating a version of stimulus-sampling theory was prepared for a digital computer and the level of learning was higher, although the improvement was gained at the expense of considerably extended running times.
Abstract: Alearning program incorporating a version of stimulus-sampling theory was prepared for a digital computer. Handwritten first name signatures coded in a 20 by 48 grid served as inputs to study the effects of parameter changes in the program. Under one main condition the computer with its program examined only those grid cells in which any part of a given pattern fell. Under a second main condition each of the 960 grid cells was examined. Learning of correct pattern names occurred under both conditions. The level of learning achieved under the second condition was higher, although the improvement was gained at the expense of considerably extended running times.
7 citations
TL;DR: I enjoyed reading Part III of the spectrum article on “Machine recognition of human language”, which reviewed in part my work on handwriting recognition, but I wish to point out one misstatement that might lead to some misleading conclusions.
Abstract: I enjoyed reading Part III of the spectrum article on “Machine recognition of human language” (May, pages 105–116), which reviewed in part my work on handwriting recognition. However, I wish to point out one misstatement that might lead to some misleading conclusions.
1 citations
1 citations