paper-with-me

홈 › Papers

Local and global topological complexity measures OF ReLU neural network functions

2022-04-12 · J. Elisenda Grigsby, Kathryn Lindsey, Marissa Masden

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.

📄 PDF Abstract BibTeX arXiv:2204.06062

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Traversing the Local Polytopes of ReLU Neural Networks

2021-11-22 · AAAI Workshop AdvML 2022 2 · Shaojie Xu, Joel Vaughan, Jie Chen, Aijun Zhang 외

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

2024-11-29 · Michal Lewandowski, Hamid Eghbalzadeh, Bernhard A. Moser

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 Augmentation

Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification

2021-11-17 · Shaojie Xu, Joel Vaughan, Jie Chen, Aijun Zhang 외

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

2019-10-18

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

2024-10-22 · J. Elisenda Grigsby, Kathryn Lindsey

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…