Abstract: A multi-stage multi-network character recognition system decomposes the estimation of a posteriori probabilities into coarse-to-fine stages. Classification is then based on the estimated a posteriori probabilities. This classification process is especially suitable for the tasks that involve a large number of categories. The multi-network system is implemented in two stages: a soft pre-classifier and a bank of multiple specialized networks. The pre-classifier performs coarse evaluation of the input character, developing different probabilities that the input character falls into different predefined character groups. The bank of specialized networks, each corresponding to a single group of characters, performs fine evaluation of the input character, where each develops different probabilities that the input character represents each character in that specialized network's respective predefined character group.

Abstract: A dental impression article made of a dental imprint material is for use with a bite fork having one or more planar members, each planar member having one or more holes. The dental imprint article includes a pad of dental imprint material that may be molded when heated. The pad of dental imprint material is for engaging a surface of planar member of the bite fork and includes a stem of dental imprint material that engages the bite fork. The stem is received through a hole in the bite fork planar member, heat is applied, and the stem is deformed, spreading beyond the hole on another surface of the planar member. When the apparatus is cooled, the dental imprint article is retained on the bite fork for use.

Abstract: In accordance with the present invention, there is provided a class of pyridine compounds which are modulators of acetylcholine receptors. The compounds of the invention displace acetylcholine receptor ligands from their binding sites.

Abstract: Improved DNA structures are disclosed which contain target sequences which bind to control proteins (such as the CREB protein). The structures of the present invention are stable to degradation, and are effective as decoys for control proteins, making it possible to modulate the transcriptional control normally exerted by such control proteins. In addition, there is provided a method to reversibly crosslink oligonucleotides to polypeptides which recognize the oligonucleotide sequence. This method involves synthesizing DNA structures as described above, wherein one or more phosphorothioate diester linkages are incorporated into the resulting oligonucleotide, allowing the phosphorothioate diester-containing oligonucleotide to bind to polypeptides which recognize the sequence of said oligonucleotide, then contacting the polypeptide-bound oligonucleotide with a transition metal reagent.