Charles W. Anderson

TL;DR: This work trains an artificial neural network (ANN) to identify the year of input maps of temperature and precipitation from forced climate model simulations and applies a neural network visualization technique to visualize the spatial patterns that lead the ANN to successfully predict the year.

TL;DR: In this paper, a neural network controller in parallel with a proportional-plus-integral (PI) feedback controller is presented for control of a process/plant in a control system, where the neural network contributes to an output of the PI controller only upon detection of at least one triggering event, at which time a value of the first set of data corresponding with the condition deviation is added-in thus, contributing to the proportional plusintegral controller.

TL;DR: In this article, the authors describe the overall research project that gave rise to the authors' paper "Neuronlike adaptive elements that can solve difficult learning control problems" that was published in the 1983 Neural and Sensory Information Processing special issue of the IEEE Transactions on Systems, Man, and Cybernetics.

TL;DR: It is demonstrated that connectionist learning networks can monitor manufacturing processes to determine causal relationships with an accuracy competitive with that of conventional statistical techniques, and with substantial savings in computational complexity as compared with conventional CIM techniques.

TL;DR: An improved IQC analysis for RNNs with time-varying weights is applied and a method of filtering control parameter updates is used to ensure stable behavior of the controlled system under adaptation of the controller.