Riemannian Geometry Cheat sheet

Riemannian Geometry Cheat sheet

Facing challenges with high-dimensional, densely packed but limited data, and complex distributions? Riemannian geometry offers a solution by enabling data scientists to grasp the true shape and distribution of data.


M, N: Manifolds,

Tp M: Tangent space, plane,

U, V: Vectors

X,Y: Vector fields

?u. Directional derivative

φ: Smooth map,

g: Metric Tensor

<,> Dot product

[X, Y] Lie bracket for vector fields,

Γij^k: Christoffel symbol,

γ: Curve on manifold



Differential geometry is a branch of mathematics that uses techniques from calculus, algebra and topology to study the properties of curves, surfaces, and higher-dimensional objects in space. It focuses on concepts such as curvature, angles, and distances, examining how these properties vary as one moves along different paths on a geometric object.

Differential geometry is crucial in understanding the shapes and structures of objects that can be continuously altered, and it has applications in many fields including physics (I.e., general relativity and quantum mechanics), engineering, computer science, and data exploration and analysis. It ultimately provides data scientists with a mathematical framework facilitates the creation of models that are accurate and complex by leveraging geometric and topological insights.



Thanks for reading. For comprehensive topics on geometric learning, including detailed analysis, reviews and exercises, subscribe to Hands-on Geometric Deep Learning


Patrick Nicolas has over 25 years of experience in software and data engineering, architecture design and end-to-end deployment and support with extensive knowledge in machine learning.?He has been director of data engineering at Aideo Technologies since 2017 and he is the?author of "Scala for Machine Learning", Packt Publishing ISBN 978-1-78712-238-3


Olabode Sule

Machine Learning/AI Leadership

8 个月

I find the notion of "curved spaces" intuitive but pre-conceived and confusing. I think of Riemannian geometry as the study of differentiable manifolds (spaces that can be modeled locally on open sets in Euclidean space, but glued together in a differentiable way ), and different ways of measuring distances in these spaces (a.k.a Riemannian metrics). We then develop a general theory of Riemannian metrics, connections and curvature which aligns with our intuitions of curved spaces embedded in Euclidean space, where we use the Euclidean metric (technically pull back) metric onto the embedded manifold.

要查看或添加评论,请登录

Patrick Nicolas的更多文章

  • Riemannian Manifolds for Geometric Learning

    Riemannian Manifolds for Geometric Learning

    Intrigued by the idea of applying differential geometry to machine learning but feel daunted? Beyond theoretical…

  • Einstein Summation in Geometric Deep Learning

    Einstein Summation in Geometric Deep Learning

    The einsum function in NumPy and PyTorch, which implements Einstein summation notation, provides a powerful and…

  • Visualization of Graph Neural Networks

    Visualization of Graph Neural Networks

    Have you ever found it challenging to represent a graph from a very large dataset while building a graph neural network…

  • Modeling Graph Neural Networks with PyTorch

    Modeling Graph Neural Networks with PyTorch

    Have you ever wondered how to get started with Graph Neural Networks (GNNs)? Torch Geometric (PyG) provides a…

  • Approximating PCA on Manifolds

    Approximating PCA on Manifolds

    Have you ever wondered how to perform Principal Component Analysis on manifolds? An approximate solution relies on the…

  • Reviews of Papers on Geometric Learning - 2024

    Reviews of Papers on Geometric Learning - 2024

    2024 introduced a fascinating collection of papers on geometric deep learning. Here are reviews of a selection of them.

    1 条评论
  • Fréchet Centroid on Manifolds in Python

    Fréchet Centroid on Manifolds in Python

    The Fréchet centroid (or intrinsic centroid) is a generalization of the concept of a mean to data points that lie on a…

  • Einstein Summation in Numpy

    Einstein Summation in Numpy

    Many research papers use Einstein summation notation to describe mathematical concepts. Wouldn't it be great to have a…

  • Deep Learning on Mac Laptop

    Deep Learning on Mac Laptop

    The latest high-performance Mac laptops are well-suited for experimentation. However, have you been frustrated by your…

    1 条评论
  • Impact of Linear Activation on Convolution Networks

    Impact of Linear Activation on Convolution Networks

    Have you ever wondered how choosing an activation function can influence the performance of a convolutional neural…

社区洞察

其他会员也浏览了