Neural network computing system for pattern recognition of thermoluminescence signature spectra and chemical defense

Abstract

A four-layer neural network is trained with data of midinfrared absorption by nerve and blister agent compounds (and simulants of this chemical group) in a standoff detection application. Known infrared absorption spectra by these analyte compounds and their computed first derivative are scaled and then transformed into binary or decimal arrays for network training by a backward-error-propagation (BEP) algorithm with gradient descent paradigm. The neural network transfer function gain and learning rate are adjusted on occasion per training session so that a global minimum in final epoch convergence is attained. Three successful neural network filters have been built around an architecture design containing: (1) an input layer of 350 neurons, one neuron per absorption intensity spanning 700.ltoreq..nu..ltoreq.1400 wavenumbers with resolution .DELTA..nu.=2; (2) two hidden layers in 256- and 128-neuron groups, respectively, providing good training convergence and adaptable for downloading to a configured group of neural IC chips; and (3) an output layer of one neuron per analyte--each analyte defined by a singular vector in the training data set. Such a neural network is preferably implemented with a network of known microprocessor chips.

Dependencies are inferred from the claim text.