Learn More
Abst ract. Learning in layered neu ral networks is posed as the mini-miz at ion of an error function defined over t he training set. A proba-bilistic interpretation of the target act ivities sugges ts th e use of rela-t ive ent ro py as an error measure. We investigate t he me rits of using this error function over t he traditional quad ratic function for(More)
A novel technique is described herein to perform a laparoscopic varicocelectomy using the high-ligation modified Palomo technique. The variation in this case is the preservation of lymphatic drainage by intraoperative identification of the lymphatics using intratesticular injection of methylene blue dye.
The Hopfield neural network. model for associative memory is generalized. The generalization replaces two state neurons by neurons taking a richer set of values. Two classes of neuron input output relations are developed guaranteeing convergence to stable states. The first is a class of "continuous" relations and the second is a class of allowed(More)
  • 1