Материал из MachineLearning.

Основная статья: Численные методы обучения по прецедентам (практика, В.В. Стрижов)

Содержание 1 Syllabus and goals 2 Theme 1: 2.1 Message 2.2 Basics 2.3 Application 2.4 Code 3 Theme 1: ODE and flows 4 Theme 1: PDE 5 Theme 1: High order splines 6 Theme 1: Topological data analysis 7 Theme 1: Homology versus homotopy 8 Fundamental theorems

• Geometric deep learning
• Functional data analysis
• Applied mathematics for machine learning

Syllabus and goals

Theme 1:

Message

Basics

Application

Code

https://papers.nips.cc/paper/2018/file/69386f6bb1dfed68692a24c8686939b9-Paper.pdf

Theme 1: ODE and flows

• Neural Ordinary Differential Equations (source paper and code)
• W: Flow-based generative model
• Flows at deepgenerativemodels.github.io
• Знакомство с Neural ODE на хабре

Goes to BME

• Variational Inference with Normalizing Flows (source paper)
• Flow-based deep generative models

Theme 1: PDE

(after RBF)

Theme 1: High order splines

Theme 1: Topological data analysis

Theme 1: Homology versus homotopy

W: Homology

Fundamental theorems

[https://en.wikipedia.org/wiki/Inverse_function_theorem W: Inverse function theorem and Jacobian