Multi-kernel neural network concurrent learning, monitoring, and forecasting system

Abstract

A multi-kernel neural network computing architecture configured to learn correlations among feature values,as the network monitors and imputes measured input values,and also predicts future output values,This computing architecture, referred to as a concurrent-learning information processor (CIP,), includes a multi-kernel neural network array,with the capability to learn and predict in real time. The CIP,also includes a manager,and an input-output transducer,that may be used for input-output refinement. These components allow the computing capacity of the multi-kernel array,to be reassigned in response to measured performance or other factors. The output feature values,computed by the multi-kernel array,and processed by an output processor,of the transducer,are supplied to a response unit,that may be configured to perform a variety of monitoring, forecasting, and control operations in response to the computed output values. Important characteristics of the CIP,such as feature function specifications,and,connection specifications,learning weight schedules,and the like may be set by a technician through a graphical user interface,Refinement processes also allow the CIP,be reconfigured in accordance with user commands for application to different physical applications.