Learn More
Two novel methods for achieving handwritten digit recognition are described. The first method is based on a neural network chip that performs line thinning and feature extraction using local template matching. The second method is implemented on a digital signal processor and makes extensive use of constrained automatic learning. Experimental results(More)
One of the most compelling and immediate applications of pervasive computing would be to use RF technology to support low-cost, long-lived and continual tracking of assets. Unfortunately, initial solutions have not yet led to widespread deployment. We believe that meeting the economic and system requirements of this application requires a redesign of the(More)
We present an application of back-propagation networks to handwritten digit recognition. Minimal preprocessing of the data was required, but architecture of the network was highly constrained and speciically designed for the task. The input of the network consists of normalized images of isolated digits. The method has 1% error rate and about a 9% reject(More)
A solution to two problems in distributed processing is described. The first problem is to obtain a proper balance between minicomputers and large machines for general-purpose timesharing. The second problem is to allow users to access several different host computers without the need to master several sets of procedures and job control languages. The(More)
This paper presents computational approach for stock market prediction. Artificial Neural Network (ANN) forms a useful tool in predicting price movement of a particular stock. In the short term, the pricing relationship between the elements of a sector holds firmly. An ANN can learn this pricing relationship to high degree of accuracy and be deployed to(More)
Superconductivity above the temperature of liquid nitrogen in copper oxide-based systems has led to optimism that superconductors may at last find wide application. The critical temperature, however, is just one of the required parameters. The materials must be made into usable forms such as wire, thick films, thin films, and bulk ceramics. In addition, the(More)
A field-effect transistor is described that combines a short-gate MOSFET with a long-channel JFET in a cascode configuration. The composite device, a CASFET, can have a very low input capacitance due to the short gate of the MOSFET combined with the reduced Miller capacitance of the cascode. The long channel of the JFET insures that the CASFET has high(More)