Youtor
Multivariate Gaussian Mixture Model Intuition amp Introduction example in TensorFlow Probability
YOUR LINK HERE:
http://youtube.com/watch?v=iqCfZEsNehQ
Multivariate Normal/Gaussian Distribution are simple and easy to work with. Let's mix multiple of them together to model feature-rich multi-variate distributions of data. Here are the notes: https://raw.githubusercontent.com/Cey... • Gaussian Mixture Models combine the simplicity of the Gaussian/Normal Distribution with the ability of combining multiple of them to model complicated distributions. We already saw their performance in the univariate case: • Gaussian Mixture Model | Intuition ... • In this video, we now want to extend the concept to Multidimensional Spaces. We therefore need to make use of the Multivariate Normal/Gaussian, which also requires some considerations with respect to the number of parameters. • In the last third of the video, we will then do a short implementation in TensorFlow Probability with scatter and contour plots. • ------- • 📝 : Check out the GitHub Repository of the channel, where I upload all the handwritten notes and source-code files (contributions are very welcome): https://github.com/Ceyron/machine-lea... • 📢 : Follow me on LinkedIn or Twitter for updates on the channel and other cool Machine Learning Simulation stuff: / felix-koehler and / felix_m_koehler • 💸 : If you want to support my work on the channel, you can become a Patreon here: / mlsim • ------- • Timestamps: • 00:00 Introduction • 01:04 Mixing Distributions • 03:19 Weighting coefficients • 04:00 Extension to more classes • 04:50 Latent class assignments • 06:32 Directed Graphical Model • 10:34 Joint Distribution • 12:22 Marginalizing the joint • 13:04 Counting number of parameters • 16:01 Three Different Forms • 18:22 Shared Parameters • 20:09 TFP: Intro • 20:27 TFP: Categorical Distribution • 20:54 TFP: Batched Multivariate Normal • 23:38 TFP: Gaussian Mixture • 24:16 TFP: Sampling • 25:23 TFP: Contour Lines • 28:25 Outro
#############################
