Title :
Fast training of recurrent networks based on the EM algorithm
Author :
Ma, Sheng ; Ji, Chuanyi
Author_Institution :
Dept. of Electr. Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
fDate :
1/1/1998 12:00:00 AM
Abstract :
In this work, a probabilistic model is established for recurrent networks. The expectation-maximization (EM) 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
Keywords :
learning (artificial intelligence); maximum likelihood estimation; probability; recurrent neural nets; EM algorithm; expectation-maximization algorithm; learning; linear weighted regression; mean-field approximation; moving target; probabilistic model; recurrent neural networks; Adaptive systems; Approximation algorithms; Computer errors; Joining processes; Neurons; Probability density function; Process control; Systems engineering and theory; Transfer functions; Vectors;
Journal_Title :
Neural Networks, IEEE Transactions on
