Convergence of the Wake-Sleep Algorithm
Ikeda, Shiro, Amari, Shun-ichi, Nakahara, Hiroyuki
–Neural Information Processing Systems
The WS (Wake-Sleep) algorithm is a simple learning rule for the models with hidden variables. It is shown that this algorithm can be applied to a factor analysis model which is a linear version of the Helmholtz machine. Buteven for a factor analysis model, the general convergence is not proved theoretically.
Neural Information Processing Systems
Dec-31-1999
- Technology: