Gaussian Mixture Model | Intuition & Introduction | TensorFlow Probability

preview_player
Показать описание

If your (univariate) distribution has more than one mode (peaks), there is a good chance you can model it with a Gaussian Mixture Model (GMM), a Mixture Distribution of Gaussian/Normal. That is helpful for a soft clustering of points in one dimension. For this you select the number of modes you expect (= the number of peaks). This will then correspond to the number of (latent) classes as well as the number of Gaussians that have to be defined.

In this video, I provide an intuition to this by looking at the grade distribution after an exam, with a first peak at 2.5 and a second peak at the grade corresponding to a fail. We will implement this model in TensorFlow Probability.

-------

-------

Timestamps:
00:00 Introduction
00:38 A Multi-Modal Distribution
01:10 Clustering of Points
02:04 A Superposition of Gaussians?
03:59 Using Mixture Coefficients
05:05 A special case of Mixture Distributions
05:33 The Directed Graphical Model
07:52 Alternative Model with plates
08:45 The joint
10:28 TFP: Defining the Parameters
11:27 TFP: The Categorical
12:12 TFP: The batched Normal
13:13 TFP: GMM in Principle
14:13 TFP: Using the TFP Mixture Distribution
15:15 TFP: Plotting the probability density
17:05 Outro
  1. Machine Learning & Simulation
  2. gmm
  3. clustering
  4. k-means
  5. soft clustering
  6. multi-modal
Рекомендации по теме
Gaussian Mixture Model 0:17:43

Gaussian Mixture Model | Intuition & Introduction | TensorFlow Probability

EM Algorithm : 0:24:08

EM Algorithm : Data Science Concepts

Multivariate Gaussian Mixture 0:28:57

Multivariate Gaussian Mixture Model | Intuition & Introduction | example in TensorFlow Probabili...

Gaussian Mixture Models 0:17:27

Gaussian Mixture Models

Gaussian Mixture Model 0:18:36

Gaussian Mixture Model | Gaussian Mixture Model in Machine Learning | GMM Explained | Simplilearn

Lec 30: Gaussian 0:51:45

Lec 30: Gaussian Mixture Model and EM Algorithm

Gaussian Mixture Model 0:15:56

Gaussian Mixture Model | Object Tracking

#96: Scikit-learn 93:Unsupervised 0:18:28

#96: Scikit-learn 93:Unsupervised Learning 1: Gaussian mixture modeling (1/5)

Machine Learning Basics: 0:07:40

Machine Learning Basics: Gaussian Mixture Models and the Expectation Maximization Algorithm

#98: Scikit-learn 95:Unsupervised 0:29:56

#98: Scikit-learn 95:Unsupervised Learning 3: Gaussian mixture modeling (3/5)

#97: Scikit-learn 94:Unsupervised 0:21:08

#97: Scikit-learn 94:Unsupervised Learning 2: Gaussian mixture modeling (2/5)

#99: Scikit-learn 96:Unsupervised 0:21:36

#99: Scikit-learn 96:Unsupervised Learning 4: Gaussian mixture modeling (4/5)

Expectation Maximization Algorithm 0:29:47

Expectation Maximization Algorithm | Intuition & General Derivation

15 Clustering and 0:26:56

15 Clustering and Mixture Models

Gaussian Mixture Models 0:26:49

Gaussian Mixture Models

Gaussian Mixture Model 0:11:58

Gaussian Mixture Model

Deriving the EM 1:13:08

Deriving the EM Algorithm for the Multivariate Gaussian Mixture Model

52b - Understanding 0:14:23

52b - Understanding Gaussian Mixture Model (GMM) using 1D, 2D, and 3D examples

Gaussian Mixture Models: 0:49:56

Gaussian Mixture Models: Theory and MATLAB Code

CS480/680 Lecture 7: 1:00:59

CS480/680 Lecture 7: Mixture of Gaussians

9.4 Gaussian Mixture 0:39:51

9.4 Gaussian Mixture Models And Expectation Maximization (UvA - Machine Learning 1 - 2020)

CS-E3210 Machine Learning: 0:35:28

CS-E3210 Machine Learning: Basic Principles - 'Soft Clustering using Gaussian Mixture Models&ap...

What is Gaussian 0:02:30

What is Gaussian Mixture Model (GMM) in Machine Learning? Decoding Gaussian Mixture Models

Expectation-Maximization | EM 0:05:58

Expectation-Maximization | EM | Algorithm Steps Uses Advantages and Disadvantages by Mahesh Huddar

Комментарии
Автор

Marginalizing the value conveyed by *your* playlist, to *my* understanding of this subject, is intractable. And if what I said is even remotely sensible, per the rules of probability, the whole credit goes to you.

karanshah
Автор

I've been following your channel for a while and you've really helped me understand complicated probability concepts, thank you! One question: I didn't understand how the z variable is a latent one. Why can't it just be a parameter?

saikeerthi
Автор

Hey, another great video! Is the GMM PDF you show at the end normalized? Thanks!

nickelandcopper
Автор

Thanks for this video. Can you make a video about multivariate case ?

engenglish
Автор

Is there a connection between using mixture coefficients to take a linear combinations of two gaussians and DGM approach, where the parameters of the gaussian parameters changes condition upon which category? They seem like 2 very different approaches to arrive at the probability. (Let me know if my question is not clear.). Thanks.

orjihvy
Автор

sorry, why the categorical distribution's P(Z) = Cat(Pi) = product of all the pi[0], pi[1]?

Breeze