mathew@elroy.jpl.nasa.gov (Mathew Yeates) (03/16/91)
Archive-name: ai/neural-nets/yeates-pseudo-kalman/1991-03-12 Archive: cheops.cis.ohio-state.edu:/pub/neuroprose/yeates.pseudo-kalman.ps.Z [128.146.8.62] Original-posting-by: mathew@elroy.jpl.nasa.gov (Mathew Yeates) Original-subject: Tech Report Available Reposted-by: emv@msen.com (Edward Vielmetti, MSEN) I the following technical report (JPL Publication) is available for anonymous ftp from the neuroprose directory at cheops.cis.ohio-state.edu. This is a short version of a previous paper "An Architecture With Neural Network Characteristics for Least Squares Problems" and has appeared in various forms at several conferences. There are two ideas that may be of interest: 1) By making the input layer of a single layer Perceptron fully connected, the learning scheme approximates Newtons algorithm instead of steepest descent. 2) By allowing local interactions between synapses the network can handle time varying behavior. Specifically, the network can implement the Kalman Filter for estimating the state of a linear system. get both yeates.pseudo-kalman.ps.Z and yeates.pseudo-kalman-fig.ps.Z A Neural Network for Computing the Pseudo-Inverse of a Matrix and Applications to Kalman Filtering Mathew C. Yeates California Institute of Technology Jet Propulsion Laboratory ABSTRACT A single layer linear neural network for associative memory is described. The matrix which best maps a set of input keys to desired output targets is computed recursively by the network using a parallel implementation of Greville's algorithm. This model differs from the Perceptron in that the input layer is fully interconnected leading to a parallel approximation to Newtons algorithm. This is in contrast to the steepest descent algorithm implemented by the Perceptron. By further extending the model to allow synapse updates to interact locally, a biologically plausible addition, the network implements Kalman filtering for a single output system.