Fast training of recurrent networks based on the EM algorithm

— In this work, a probabilistic model is established for recurrent networks. The EM (expectation-maximization) algorithm is then applied to derive a new fast training algorithm for recurrent networks through mean-field approximation. This new algorithm converts training a complicated recurrent network into training an array of individual feedforward neurons. These neurons are then trained via a linear weighted regression algorithm. The training time has been improved by five to 15 times on benchmark problems.

• Type: Journal
• Year: 1998
• Where: TNN
• Authors: Sheng Ma, Chuanyi Ji
• Keywords: Algorithm, Fast Training Algorithm, Recurrent Network, TNN 1998