A Framework for the construction of upper bounds on the number of affine linear regions of ReLU feed-forward neural networks

06/05/2018
by   Peter Hinz, et al.
0

In this work we present a new framework to derive upper bounds on the number regions of feed-forward neural nets with ReLU activation functions. We derive all existing such bounds as special cases, however in a different representation in terms of matrices. This provides new insight and allows a more detailed analysis of the corresponding bounds. In particular, we provide a Jordan-like decomposition for the involved matrices and present new tighter results for an asymptotic setting. Moreover, new even stronger bounds may be obtained from our framework.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset