Участник:Strijov/Drafts

(Различия между версиями)

Версия 21:29, 6 сентября 2021

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

@@ Строка 2: / Строка 2: @@
 {{TOCright}}
-* Geometric deep learning
-* Functional data analysis
-* Applied mathematics for machine learning
-==Syllabus and goals==
-==Theme 1: ==
-===Message===
-===Basics===
+=Fundamental theorems=
+[https://en.wikipedia.org/wiki/Inverse_function_theorem W: Inverse function theorem and Jacobian]
-===Application===
-===Code===
-https://papers.nips.cc/paper/2018/file/69386f6bb1dfed68692a24c8686939b9-Paper.pdf
-==Theme 1: ODE and flows==
-*[https://papers.nips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html Neural Ordinary Differential Equations] (source paper and code)
-*[https://en.wikipedia.org/wiki/Flow-based_generative_model W: Flow-based generative model]
-*[https://deepgenerativemodels.github.io/notes/flow/ Flows at deepgenerativemodels.github.io]
-*[https://habr.com/ru/company/ods/blog/442002/ Знакомство с Neural ODE на хабре]
-Goes to BME
-*[https://arxiv.org/pdf/1505.05770.pdf Variational Inference with Normalizing Flows (source paper)]
-*[https://lilianweng.github.io/lil-log/2018/10/13/flow-based-deep-generative-models.html Flow-based deep generative models]
-==Theme 1: PDE==