Estimate of the Neural Net Dimension Using Algebraic Topology and Lie Theory

04/06/2020
by   Luciano Melodia, et al.
0

In this paper we present an approach to determine the smallest possible number of perceptrons in a neural net in such a way that the topology of the input space can be learned sufficiently well. We introduce a general procedure based on persistent homology to investigate topological invariants of the manifold on which we suspect the data set. We specify the required dimensions precisely, assuming that there is a smooth manifold on or near which the data are located. Furthermore, we require that this space is connected and has a commutative group structure in the mathematical sense. These assumptions allow us to derive a decomposition of the underlying space whose topology is well known. We use the representatives of the k-dimensional homology groups from the persistence landscape to determine an integer dimension for this decomposition. This number is the dimension of the embedding that is capable of capturing the topology of the data manifold. We derive the theory and validate it experimentally on toy data sets.

READ FULL TEXT
research
04/06/2020

Estimate of the Neural Network Dimension Using Algebraic Topology and Lie Theory

In this paper, we present an approach to determine the smallest possible...
research
04/06/2020

Parametrization of Neural Networks with Connected Abelian Lie Groups as Data Manifold

Neural nets have been used in an elusive number of scientific discipline...
research
09/30/2022

TOAST: Topological Algorithm for Singularity Tracking

The manifold hypothesis, which assumes that data lie on or close to an u...
research
09/20/2017

Persistence Flamelets: multiscale Persistent Homology for kernel density exploration

In recent years there has been noticeable interest in the study of the "...
research
03/11/2023

Finding large counterexamples by selectively exploring the Pachner graph

We often rely on censuses of triangulations to guide our intuition in 3-...
research
10/27/2020

Computation of Large Asymptotics of 3-Manifold Quantum Invariants

Quantum topological invariants have played an important role in computat...
research
09/05/2022

Effective Estimation of the Dimensions of a Manifold from Random Samples

We give explicit theoretical and heuristical bounds for how big does a d...

Please sign up or login with your details

Forgot password? Click here to reset