Representation of 2D frame less visual space as a neural manifold and its information geometric interpretation

• URL: http://arxiv.org/abs/2011.13585v1
• Date: Fri, 27 Nov 2020 07:21:43 GMT
• Title: Representation of 2D frame less visual space as a neural manifold and its information geometric interpretation
• Authors: Debasis Mazumdar
• Abstract summary: The origin of hyperbolic nature of the visual space is investigated using evidences from neuroscience. The processing of spatial information in the human brain can be modeled in a parametric probability space endowed with Fisher-Rao metric.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Representation of 2D frame less visual space as neural manifold and its modelling in the frame work of information geometry is presented. Origin of hyperbolic nature of the visual space is investigated using evidences from neuroscience. Based on the results we propose that the processing of spatial information, particularly estimation of distance, perceiving geometrical curves etc. in the human brain can be modeled in a parametric probability space endowed with Fisher-Rao metric. Compactness, convexity and differentiability of the space is analysed and found that they obey the axioms of G space, proposed by Busemann. Further it is shown that it can be considered as a homogeneous Riemannian space of constant negative curvature. It is therefore ensured that the space yields geodesics into it. Computer simulation of geodesics representing a number of visual phenomena and advocating the hyperbolic structure of visual space is carried out. Comparison of the simulated results with the published experimental data is presented.

Related papers

• Spherinator and HiPSter: Representation Learning for Unbiased Knowledge Discovery from Simulations [0.0]
  We describe a new, unbiased, and machine learning based approach to obtain useful scientific insights from a broad range of simulations. Our concept is based on applying nonlinear dimensionality reduction to learn compact representations of the data in a low-dimensional space. We present a prototype using a rotational invariant hyperspherical variational convolutional autoencoder, utilizing a power distribution in the latent space, and trained on galaxies from IllustrisTNG simulation.
  arXiv  Detail & Related papers  (2024-06-06T07:34:58Z)
• Quantum Scattering of Spinless Particles in Riemannian Manifolds [0.0]
  Quantum mechanics is sensitive to the geometry of the underlying space. We present a framework for quantum scattering of a non-relativistic particle confined to a two-dimensional space.
  arXiv  Detail & Related papers  (2024-02-16T10:50:50Z)
• Improving embedding of graphs with missing data by soft manifolds [51.425411400683565]
  The reliability of graph embeddings depends on how much the geometry of the continuous space matches the graph structure. We introduce a new class of manifold, named soft manifold, that can solve this situation. Using soft manifold for graph embedding, we can provide continuous spaces to pursue any task in data analysis over complex datasets.
  arXiv  Detail & Related papers  (2023-11-29T12:48:33Z)
• Alignment and Outer Shell Isotropy for Hyperbolic Graph Contrastive Learning [69.6810940330906]
  We propose a novel contrastive learning framework to learn high-quality graph embedding. Specifically, we design the alignment metric that effectively captures the hierarchical data-invariant information. We show that in the hyperbolic space one has to address the leaf- and height-level uniformity which are related to properties of trees.
  arXiv  Detail & Related papers  (2023-10-27T15:31:42Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• Shape And Structure Preserving Differential Privacy [70.08490462870144]
  We show how the gradient of the squared distance function offers better control over sensitivity than the Laplace mechanism. We also show how using the gradient of the squared distance function offers better control over sensitivity than the Laplace mechanism.
  arXiv  Detail & Related papers  (2022-09-21T18:14:38Z)
• Geometry Interaction Knowledge Graph Embeddings [153.69745042757066]
  We propose Geometry Interaction knowledge graph Embeddings (GIE), which learns spatial structures interactively between the Euclidean, hyperbolic and hyperspherical spaces. Our proposed GIE can capture a richer set of relational information, model key inference patterns, and enable expressive semantic matching across entities.
  arXiv  Detail & Related papers  (2022-06-24T08:33:43Z)
• The Geometry of Deep Generative Image Models and its Applications [0.0]
  Generative adversarial networks (GANs) have emerged as a powerful unsupervised method to model the statistical patterns of real-world data sets. These networks are trained to map random inputs in their latent space to new samples representative of the learned data. The structure of the latent space is hard to intuit due to its high dimensionality and the non-linearity of the generator.
  arXiv  Detail & Related papers  (2021-01-15T07:57:33Z)
• Ultrahyperbolic Representation Learning [13.828165530602224]
  In machine learning, data is usually represented in a (flat) Euclidean space where distances between points are along straight lines. We propose a representation living on a pseudo-Riemannian manifold of constant nonzero curvature. We provide the necessary learning tools in this geometry and extend gradient-based optimization techniques.
  arXiv  Detail & Related papers  (2020-07-01T03:49:24Z)
• Geometry of Similarity Comparisons [51.552779977889045]
  We show that the ordinal capacity of a space form is related to its dimension and the sign of its curvature. More importantly, we show that the statistical behavior of the ordinal spread random variables defined on a similarity graph can be used to identify its underlying space form.
  arXiv  Detail & Related papers  (2020-06-17T13:37:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.