Gregory L. Tarr

Learn More
This paper presents a probability of error based method of determining the saliency (usefulness) of input features and hidden nodes. We show that the partial derivative of the output nodes with respect to a given input feature yields a sensitivity measure for the probability of error. This partial derivative provides a saliency metric for determining the(More)
This paper presents the first physiologically motivated pulse coupled neural network (PCNN)-based image fusion network for object detection. Primate vision processing principles, such as expectation driven filtering, state dependent modulation, temporal synchronization, and multiple processing paths are applied to create a physiologically motivated image(More)
Summary form only given, as follows. Artificial neural network topologies which use both self-organization and supervised learning are discussed. Aberrations in counterpropagation are shown. A hybrid-network is developed and shown to be more efficient than backward error propagation alone for the tactical target recognition problem considered. The hybrid(More)
  • 1