Title :
Valley searching method for recurrent neural networks
Author :
Gouhara, Kazutoshi ; Yokoi, Kunio ; Uchikawa, Yoshiki
Author_Institution :
Nagoya Univ., Japan
Abstract :
The authors present a new learning algorithm called the VSM (valley searching method) for the supervised learning of RNNs (recurrent neural networks). H. Akaike had originally proposed to accelerate a search for a minimum of the quadratic function with a positive definite symmetric matrix. It is shown that VSM is very effective for searching for a minimum in the shape of the curved narrow valley peculiar to the RNN learning surface where learning is executed
Keywords :
learning (artificial intelligence); recurrent neural nets; curved narrow valley; learning algorithm; learning surface; positive definite symmetric matrix; quadratic function; recurrent neural networks; valley searching method; Acceleration; Cost function; Differential equations; Multi-layer neural network; Neural networks; Neurons; Recurrent neural networks; Shape; Supervised learning; Symmetric matrices;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227073
