论文信息 - Sorting with Self-Organizing Maps

Sorting with Self-Organizing Maps

A self-organizing feature map (Von der Malsburg 1973; Kohonen 1984) sorts n real numbers in O(n) time apparently violating the O(n log n) bound. Detailed analysis shows that the net takes advantage of the uniform distribution of the numbers and, in this case, sorting in O(n) is possible. There are, however, an exponentially small fraction of pathological distributions producing O(n2) sorting time. It is interesting to observe that standard learning produced a smart sorting algorithm.

Marco Budinich | M. Budinich

[1] Donald E. Knuth,et al. The Art of Computer Programming: Volume 3: Sorting and Searching , 1998 .

[2] Alfred V. Aho,et al. The Design and Analysis of Computer Algorithms , 1974 .

[3] Roman Bek,et al. Discourse on one way in which a quantum-mechanics language on the classical logical base can be built up , 1978, Kybernetika.

[4] Teuvo Kohonen,et al. Self-Organization and Associative Memory , 1988 .

[5] Geszti,et al. Criticality in the one-dimensional Kohonen neural map. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[6] Helge J. Ritter,et al. Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[7] John G. Taylor,et al. On the Ordering Conditions for Self-Organizing Maps , 1995, Neural Computation.