Local and global topological complexity measures OF ReLU neural network functions
We apply a generalized piecewise-linear (PL) version of Morse theory due to Grunert-Kuhnel-Rote to define and study new local and global notions of topological complexity for fully-connected feedforward ReLU neural network functions, F: R^n -> R. Along the way, we show how to construct, for each such F, a canonical polytopal complex K(F) and a deformation retract of the domain onto K(F), yielding a convenient compact model for performing calculations. We also give a construction showing that local complexity can be arbitrarily high.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Traversing the Local Polytopes of ReLU Neural Networks
Although neural networks (NNs) with ReLU activation functions have found success in a wide range of applications, their adoption in risk-sensitive settings has been limited by the concerns on robustness and interpretabil…
CantorNet: A Sandbox for Testing Geometrical and Topological Complexity Measures
Many natural phenomena are characterized by self-similarity, for example the symmetry of human faces, or a repetitive motif of a song. Studying of such symmetries will allow us to gain deeper insights into the underlying…
Data AugmentationTraversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification
Although neural networks (NNs) with ReLU activation functions have found success in a wide range of applications, their adoption in risk-sensitive settings has been limited by the concerns on robustness and interpretabil…
A multilevel analysis to systemic exposure: insights from local and system-wide information
In the aftermath of the financial crisis, the growing literature on financial networks has widely documented the predictive power of topological characteristics (e.g. degree centrality measures) to explain the systemic i…
On Functional Dimension and Persistent Pseudodimension
For any fixed feedforward ReLU neural network architecture, it is well-known that many different parameter settings can determine the same function. It is less well-known that the degree of this redundancy is inhomogeneo…