Learning algorithms for probabilistic neural nets

Although neural net models show great promise in areas where traditional AI approaches falter, such as pat tern recognition, pat tern completion and content addressable memory, their success is constrained by slow learning rates and the d i f f i cu l ty of phys ica l i m p l e m e n t a t i o n ; l e a r n i n g s t r a t e g i e s such as error-back-propagation are also implausible as biological models.