Temporal sequence storage

Abstract Two approaches to the storage of temporal sequences are described which both use the temporal properties of neurons. One of them uses a feedback architecture with coupled nets. The other develops a topographic map for temporal neurons. Possible biological realisation of these methods are discussed.

[1]  E. Gardner.  The space of interactions in neural network models , 1988 .

[2]  John G. Taylor,et al.  Storing temporal sequences , 1991, Neural Networks.

[3]  C. Malsburg,et al.  How patterned neural connections can be set up by self-organization , 1976, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[4]  Teuvo Kohonen,et al.  The 'neural' phonetic typewriter , 1988, Computer.

[5]  John G. Taylor,et al.  Neural Network Capacity for Temporal Sequence Storage , 1991, Int. J. Neural Syst..

[6]  Barak A. Pearlmutter.  Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.