| Summary: | Artificial neural networks are brain-like models of parallel computations and cognitive phenomena. We sample some basic results about neural networks as they relate to stochastic and statistical processes. Given the explosivo amount of material, only models bearing a stochastic component in the function or analysis are presented, such as Hopfield and feedforward nets, Boltzman machines and some recurrent networks. Basic algorithms for learning such as backpropagation and gradient descent are sketched. A handful of applications (associative memories, pattem recognition, time series forecast) aredescribed. Finally, some current trends in the field are discussed.
|
|---|