Feed-forward neural networks: a geometrical perspective
Marco Budinich, E. Milotti · Journal of Physics A Mathematical and General · 1991
The convex hull of any subset of vertices of an n-dimensional hypercube contains no other vertex of the hypercube. This result permits the application of some theorems of n-dimensional geometry to digital feed-forward neural networks. Also, the construction of the convex hull is proposed as an alternative to more traditional learning algorithms. Some preliminary simulation results are reported.