Tutorials

优质

小牛编辑

122浏览

2023-12-01

Tutorials

Edward provides a testbed for rapid experimentation and research with probabilistic http://edwardlib.org/tutorials/models. Here we show how to apply this process for diverse learning tasks.

Bayesian linear regression
A fundamental http://edwardlib.org/tutorials/model for supervised learning.

Batch training
How to train a http://edwardlib.org/tutorials/model using only minibatches of data at a time.

TensorBoard
Visualize learning, explore the computational graph, and diagnose training problems.

Automated transformations
Using transformations to easily work over constrained continuous support.

Linear mixed effects http://edwardlib.org/tutorials/models
Linear http://edwardlib.org/tutorials/modeling of fixed and random effects.

Gaussian process classification
Learning a distribution over functions for supervised classification.

Mixture http://edwardlib.org/tutorials/models
Unsupervised learning by clustering data points.

Latent space http://edwardlib.org/tutorials/models
Analyzing connectivity patterns in neural data.

Mixture density networks
A neural density estimator for solving inverse problems.

Generative adversarial networks
Building a deep generative http://edwardlib.org/tutorials/model of MNIST digits.

Probabilistic http://edwardlib.org/tutorials/decoder
A http://edwardlib.org/tutorials/model of latent codes in information theory.

Inference networks
How to amortize computation for training and testing http://edwardlib.org/tutorials/models.

Bayesian neural network
Bayesian analysis with neural networks.

Probabilistic PCA
Dimensionality reduction with latent variables.

If you’re interested in contributing a tutorial, checking out the contributing page.

Videos

Probabilistic Programming with GPs by Dustin Tran. Gaussian Process Summer School, 09/2017.
Intro to Bayesian Machine Learning with PyMC3 and Edward by Torsten Scholak, Diego Maniloff. PyCon, 05/2017.
Bayesian Deep Learning with Edward (and a trick using Dropout) by Andrew Rowan. PyData London, 05/2017.
Edward: A library for probabilistic http://edwardlib.org/tutorials/modeling, http://edwardlib.org/tutorials/inference, and http://edwardlib.org/tutorials/criticism by Dustin Tran. NYU ML Meetup, 01/2017.
Edward: A library for probabilistic http://edwardlib.org/tutorials/modeling, http://edwardlib.org/tutorials/inference, and http://edwardlib.org/tutorials/criticism by Dustin Tran. Twitter, 09/2016.

We also have a community repository for sharing content such as papers, posters, and slides.

Background

For more background and notation, see the pages below.

There are also companion webpages for several papers about Edward.

"Deep probabilistic programming" at ICLR 2017