Estimate of the Neural Network Dimension Using Algebraic Topology and Lie Theory
In this paper we present an approach to determine the smallest possible number of neurons in a layer of a neural network 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.
Code (1)
Similar Papers 제목 키워드 기반
Policies for constraining the behaviour of coalitions of agents in the context of algebraic information theory
This article takes an oblique sidestep from two previous papers, wherein an approach to reformulation of game theory in terms of information theory, topology, as well as a few other notions was indicated. In this documen…
Cycle Representation Learning for Inductive Relation Prediction
In recent years, algebraic topology and its modern development, the theory of persistent homology, has shown great potential in graph representation learning. In this paper, based on the mathematics of algebraic topology…
Graph Representation LearningInductive Relation PredictionKnowledge Graph CompletionKnowledge Graphs+4Understanding Deep Learning using Topological Dynamical Systems, Index Theory, and Homology
In this paper we investigate Deep Learning Models using topological dynamical systems, index theory, and computational homology. These mathematical machinery was invented initially by Henri Poincare around 1900 and devel…
Chordless cycle filtrations for dimensionality detection in complex networks via topological data analysis
Many complex networks, ranging from social to biological systems, exhibit structural patterns consistent with an underlying hyperbolic geometry. Revealing the dimensionality of this latent space can disentangle the struc…
Uniform Manifold Approximation and Projection (UMAP) and its Variants: Tutorial and Survey
Uniform Manifold Approximation and Projection (UMAP) is one of the state-of-the-art methods for dimensionality reduction and data visualization. This is a tutorial and survey paper on UMAP and its variants. We start with…
Data VisualizationDimensionality Reduction