Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)
Jose C. Principe, Hui-H. Hsu, Jyh-Ming Kuo
Short term memory is indispensable for the processing of time varying information with artificial neural networks. In this paper a model for linear memories is presented, and ways to include memories in connectionist topologies are discussed. A comparison is drawn among different memory types, with indication of what is the salient characteristic of each memory model.