The principal purpose of this research is to discover the underlying properties of linear multilevel threshold devices and networks of linear multilevel threshold devices. The main theoretical developments of this investigation entail generalizing the function-counting theorem associated with linear bi-level threshold devices to that of linear multilevel threshold devices. The investigation reveals surprising connections that underlie linear inequalities, linear separability, linear ordering, and region counting. The results have implications in the field of geometric probability. Computations based on theoretical analysis support Brown's (1964) conjecture and suggest that k/(k-1) is a natural definition for the information-storage capacity of a k-level threshold device. A lower bound on the number of weights required to implement a universal network of k-level threshold devices is derived. Finally, it is shown that the Vapnik-Chervonenki (1971)s dimension (VC-dimension) for the class of multilevel threshold function is d+1 for pattern vectors in /spl Rscr//sup d/. This VC-dimension is also linked to an error-rate bound for multilevel threshold functions within the framework of uniform learnability.

This paper presents new upper and lower bounds on the minimum probability of error of Bayesian decision systems for the two-class problem. These bounds can be made arbitrarily close to the exact minimum probability of error, making them tighter than any previously known bounds.

Optical character recognition (OCR) refers to a process whereby printed documents are transformed into ASCII files for the purpose of compact storage, editing, fast retrieval, and other file manipulations through the use of a computer. The recognition stage of an OCR process is made difficult by added noise, image distortion, and the various character typefaces, sizes, and fonts that a document may have. In this study a neural network approach is introduced to perform high accuracy recognition on multi-size and multi-font characters; a novel centroid-dithering training process with a low noise-sensitivity normalization procedure is used to achieve high accuracy results. The study consists of two parts. The first part focuses on single size and single font characters, and a two-layered neural network is trained to recognize the full set of 94 ASCII character images in 12-pt Courier font. The second part trades accuracy for additional font and size capability, and a larger two-layered neural network is trained to recognize the full set of 94 ASCII character images for all point sizes from 8 to 32 and for 12 commonly used fonts. The performance of these two networks is evaluated based on a database of more than one million character images from the testing data set.>

This paper presents four lossless acceleration algorithms for a special type of nearest-neighbor pattern recognition whereby correlation functions are used. The algorithms are called template stopping, template ordering, pixel stopping, and pixel ordering. All four algorithms may be used either independently or simultaneously to accelerate the nearest-neighbor search without incurring any loss to accuracy. To illustrate their usefulness, all four algorithms are demonstrated on an optical character recognition system.