Title :
Incremental learning of temporal sequences using state memory and a resource allocating network
Author :
Konishi, Yoshio ; Fujii, Robert H.
Author_Institution :
Dept. of Comput. Eng., Aizu Univ., Japan
Abstract :
A network, which can learn temporal patterns incrementally, is proposed. The network uses: a) Gaussian functions to represent various output values and b) chunking to group similar patterns so that a compact network can be realized. The learning capacity limits of the network are evaluated for the worst case sequences. Learning of sequences can be performed using a simple one step algorithm.
Keywords :
Gaussian processes; learning (artificial intelligence); pattern clustering; resource allocation; sequences; Gaussian function; incremental learning; resource allocating network; state memory; temporal sequences; Animals; Computer networks; Electronic mail; Motion pictures; Neural networks; Neurofeedback; Output feedback; Resource management; Robot control; Trajectory;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1381118
