288 pp. per issue
6 x 9, illustrated
2014 Impact factor:

Neural Computation

August 2020, Vol. 32, No. 8, Pages 1431-1447
(doi: 10.1162/neco_a_01295)
© 2020 Massachusetts Institute of Technology
Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective
Article PDF (308.86 KB)
It is known that any target function is realized in a sufficiently small neighborhood of any randomly connected deep network, provided the width (the number of neurons in a layer) is sufficiently large. There are sophisticated analytical theories and discussions concerning this striking fact, but rigorous theories are very complicated. We give an elementary geometrical proof by using a simple model for the purpose of elucidating its structure. We show that high-dimensional geometry plays a magical role. When we project a high-dimensional sphere of radius 1 to a low-dimensional subspace, the uniform distribution over the sphere shrinks to a gaussian distribution with negligibly small variances and covariances.