Главная
Study mode:
on
1
Introduction
2
Overview
3
Persistent homology
4
Persistence pipeline
5
metric space
6
different approaches
7
persistence landscapes
8
Persistence images
9
Parameters
10
Implementation
11
Examples
12
Stability
13
Data
14
Distance matrices
15
Resolution and variance
16
Classification
Description:
Explore persistent homology and persistence images in this comprehensive lecture from the Applied Algebraic Topology Network. Dive into the world of topological data analysis, learning how to characterize the underlying structure of noisy data sets. Discover the concept of persistence diagrams (PDs) and their transformation into persistence images (PIs). Understand the stability of this transformation and its advantages in machine learning tasks. Compare the discriminatory power of PIs against existing methods and explore their application with vector-based machine learning tools. Examine real-world applications, including parameter inference from dynamic systems and partial differential equations. Follow the lecture's progression through topics such as metric spaces, persistence landscapes, implementation techniques, and classification methods.

Persistence Images

Applied Algebraic Topology Network
Add to list
0:00 / 0:00