## Concurrent Learning and Information Processing: A Neuro-computing System that Learns During Monitoring, Forecasting, and ControlMany monitoring, forecasting, and control operations occur in settings where relationships among key measurements must be learned quickly. Examples are on-line industrial processes where influent material is not consistent over time, energy load or price forecasting where demand characteristics change rapidly, and health management where relationships among monitored variables must be learned for each patient-treatment combination. The solution presented is a neuro-computing system that learns in real-time, even when data arrival rates are several million measurements per second. This text describes benefits and features of the system, statistical foundations for the system, and several related models. It also describes available system software. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

RAPID LEARNING FEATURES | 61 |

RAPID LEARNING FOUNDATIONS | 131 |

OPERATIONAL DETAILS | 211 |

Copyright | |

1 other sections not shown

### Other editions - View all

Concurrent Learning and Information Processing: A Neuro-Computing System ... Robert J. Jannarone No preview available - 2011 |

### Common terms and phrases

analysis applications backpropagation binary and categorical categorical measurement categorical variables chapter Clip Neural Systems coefficient computed concurrent learning connection weights control signals correlation corresponding Courtesy of Rapid covariance cross-products default deviance statistics deviant measurements Display example feature function Figure Graphical User Interface identify independent variables information processing initial input measurements input-output iterative Learner learning and prediction learning weight linear linear regression mean feature meas measurement features monitoring multivariate neural network neuro-computing neuron off-line open-loop control options output performed PID controllers pixel plausibility values power features pre-programming predicted values prediction functions problems produce Rapid Clip Neural rapid learning methods rapid learning operations rapid learning software rapid learning system rates real-time redundant refinement operations regression weights relationships requires sample-based specifications statistical estimation strain gauge tank level tion tolerance band Transducer trend trial univariate update learning urements User-Supplied variance vector viability values