Inman Harvey, James V. Stone
We demonstrate that imperfect recall of a set of associations can be improved by training on most new, unrelated sets of associations. This `spontaneous' recovery of associations is a consequence of the high dimensionality of weight spaces, and is therefore not peculiar to any single type of neural net. Accordingly, this work may have implications for spontaneous recovery of memory in the central nervous system.
Download compressed postscript file