论文信息 - Pattern separation in digital learning nets

Pattern separation in digital learning nets

Pattern separation is a new technique in digital learning networks which can be used to detect state conflicts. This letter describes pattern separation in a simple single-layer network, and an application of the technique in networks with feedback.

John Mark Bishop | Richard Mitchell | S. E. Pepper | D.L.P. Aitken

[1] E. H. Mamdani,et al. Microcircuit learning nets: improved recognition by means of pattern feedback , 1968 .

[2] Teuvo Kohonen,et al. Associative memory. A system-theoretical approach , 1977 .

[3] T. J. Stonham,et al. Guide to pattern recognition using random-access memories , 1979 .

[4] I. Aleksander. Microcircuit learning nets: Hamming-distance behaviour , 1970 .