What are Normalizing Flows?
This short tutorial covers the basics of normalizing flows, a technique used in machine learning to build up complex probability distributions by transforming simple ones.
Papers to check out:
NICE: Non-linear Independent Components Estimation (https://arxiv.org/abs/1410.8516)
Density estimation using Real NVP (https://arxiv.org/abs/1605.08803)
Glow: Generative Flow with Invertible 1x1 Convolutions (https://arxiv.org/abs/1807.03039)
Variational Inference with Normalizing Flows (https://arxiv.org/abs/1505.05770)
Improving Variational Inference with Inverse Autoregressive Flow (https://arxiv.org/abs/1606.04934)
Masked Autoregressive Flow for Density Estimation (https://arxiv.org/abs/1705.07057)
MADE: Masked Autoencoder for Distribution Estimation (https://arxiv.org/abs/1502.03509)
Discrete Flows: Invertible Generative Models of Discrete Data (https://arxiv.org/abs/1905.10347)
Earlier work on flows:
A family of non-parametric density estimation algorithms (https://math.nyu.edu/faculty/tabak/publications/Tabak-Turner.pdf)
Additional reading:
https://deepgenerativemodels.github.io/notes/flow/
https://blog.evjang.com/2018/01/nf1.html
https://lilianweng.github.io/lil-log/2018/10/13/flow-based-deep-generative-models.html
http://akosiorek.github.io/ml/2018/04/03/norm_flows.html
Special thanks to Alex Beatson, Geoffrey Roeder, Yaniv Ovadia, Sachin Ravi, and Ryan Adams for helpful feedback on this video.
Video style inspired by 3Blue1Brown
Music: Trinkets by Vincent Rubinetti
Видео What are Normalizing Flows? канала Ari Seff
Papers to check out:
NICE: Non-linear Independent Components Estimation (https://arxiv.org/abs/1410.8516)
Density estimation using Real NVP (https://arxiv.org/abs/1605.08803)
Glow: Generative Flow with Invertible 1x1 Convolutions (https://arxiv.org/abs/1807.03039)
Variational Inference with Normalizing Flows (https://arxiv.org/abs/1505.05770)
Improving Variational Inference with Inverse Autoregressive Flow (https://arxiv.org/abs/1606.04934)
Masked Autoregressive Flow for Density Estimation (https://arxiv.org/abs/1705.07057)
MADE: Masked Autoencoder for Distribution Estimation (https://arxiv.org/abs/1502.03509)
Discrete Flows: Invertible Generative Models of Discrete Data (https://arxiv.org/abs/1905.10347)
Earlier work on flows:
A family of non-parametric density estimation algorithms (https://math.nyu.edu/faculty/tabak/publications/Tabak-Turner.pdf)
Additional reading:
https://deepgenerativemodels.github.io/notes/flow/
https://blog.evjang.com/2018/01/nf1.html
https://lilianweng.github.io/lil-log/2018/10/13/flow-based-deep-generative-models.html
http://akosiorek.github.io/ml/2018/04/03/norm_flows.html
Special thanks to Alex Beatson, Geoffrey Roeder, Yaniv Ovadia, Sachin Ravi, and Ryan Adams for helpful feedback on this video.
Video style inspired by 3Blue1Brown
Music: Trinkets by Vincent Rubinetti
Видео What are Normalizing Flows? канала Ari Seff
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Introduction to Normalizing Flows (ECCV2020 Tutorial)Variational AutoencodersCS480/680 Lecture 23: Normalizing flows (Priyank Jaini)DATA STRUCTURES you MUST know (as a Software Developer)How (and why) to raise e to the power of a matrix | DE6What are Transformers?Heroes of Deep Learning: Andrew Ng interviews Ian GoodfellowInvertible Neural Networks and Inverse ProblemsL3 Flow Models -- CS294-158-SP20 Deep Unsupervised Learning -- UC Berkeley -- Spring 2020The Mathematics of Machine LearningA.I. teaches itself to drive in TrackmaniaLaurent Dinh: "A primer on normalizing flows"CNN: Convolutional Neural Networks Explained - ComputerphileFeynman's Lost Lecture (ft. 3Blue1Brown)How to Normalize a Wave function in Quantum MechanicsMarI/O - Machine Learning for Video GamesAn introduction to Reinforcement LearningCUDA Explained - Why Deep Learning uses GPUsMax Welling - Make VAEs Great Again: Unifying VAEs and FlowsLecture 13 | Generative Models