Title :
Reinforcement learning in associative memory
Author :
Zhu, Shaojuan ; Hammerstrom, Dan
Author_Institution :
Dept. of ECE, Oregon Health & Sci. Univ., OR, USA
Abstract :
A reinforcement learning based associative memory structure (RLAM) is proposed. In this structure, a one-layer feed forward Palm [Palm, G., 1980] model is applied to the networks. Instead of batch training, an on-line learning method is used to construct the memory. The networks are trained interactively according to reinforcement learning, which is biologically plausible. The experiment results show that the networks converge and generalize well.
Keywords :
Hebbian learning; cognitive systems; content-addressable storage; feedforward; robots; Hebbian learning; associative memory structure; cognitive process; feed forward Palm model; incremental learning; online learning method; reinforcement learning; robotic system; Associative memory; Biological system modeling; Biology; Brain modeling; Feeds; Learning systems; Muscles; Process planning; Robustness; Table lookup;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223891
