Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Comparing Neural Networks via Generalized Persistence

Applied Algebraic Topology Network via YouTube

Overview

Explore the application of rank-based persistence in comparing neural network architectures in this 49-minute conference talk. Delve into a generalized persistence framework that characterizes data representations at each layer of artificial neural networks. Learn about the theoretical approach, including generalized categories, fiberwise rank functions, and categorical persistence. Discover how persistence diagrams, multicolor persistence, and levelpoint clouds fit into this generalized framework. Examine practical applications, focusing on data distribution, weighted graphs, and optimal agent group actions. Gain insights into the results of comparing different neural architectures using this innovative approach, bridging the gap between artificial neural networks and topological persistence.

Syllabus

Introduction
Motivations
Theoretical Approach
Basic Ingredients
Generalized Categories
Fiberwise Rank Functions
Categorical Persistence
Summary
Persistence Diagrams
Multicolor Persistence
Levelpoint Clouds
Generalized Framework
Applications
Data Distribution
Results
Weighted Graph
Blocks
Optimal Agent
Group Action

Taught by

Applied Algebraic Topology Network

Reviews

Start your review of Comparing Neural Networks via Generalized Persistence

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.