All Projects → mirceamironenco → Bayesianrecurrentnn

mirceamironenco / Bayesianrecurrentnn

Licence: mit
Implementation of Bayesian Recurrent Neural Networks by Fortunato et. al

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Bayesianrecurrentnn

Rethinking Pyro
Statistical Rethinking with PyTorch and Pyro
Stars: ✭ 116 (-42.29%)
Mutual labels:  bayesian-inference
Particles
Sequential Monte Carlo in python
Stars: ✭ 135 (-32.84%)
Mutual labels:  bayesian-inference
Sbi
Simulation-based inference in PyTorch
Stars: ✭ 164 (-18.41%)
Mutual labels:  bayesian-inference
Exoplanet
Fast & scalable MCMC for all your exoplanet needs!
Stars: ✭ 122 (-39.3%)
Mutual labels:  bayesian-inference
Glmm In Python
Generalized linear mixed-effect model in Python
Stars: ✭ 131 (-34.83%)
Mutual labels:  bayesian-inference
Celeste.jl
Scalable inference for a generative model of astronomical images
Stars: ✭ 142 (-29.35%)
Mutual labels:  bayesian-inference
A Nice Mc
Code for "A-NICE-MC: Adversarial Training for MCMC"
Stars: ✭ 115 (-42.79%)
Mutual labels:  bayesian-inference
Dynamichmc.jl
Implementation of robust dynamic Hamiltonian Monte Carlo methods (NUTS) in Julia.
Stars: ✭ 172 (-14.43%)
Mutual labels:  bayesian-inference
Mrbayes
MrBayes is a program for Bayesian inference and model choice across a wide range of phylogenetic and evolutionary models. For documentation and downloading the program, please see the home page:
Stars: ✭ 131 (-34.83%)
Mutual labels:  bayesian-inference
Beast2
Bayesian Evolutionary Analysis by Sampling Trees
Stars: ✭ 156 (-22.39%)
Mutual labels:  bayesian-inference
Vbmc
Variational Bayesian Monte Carlo (VBMC) algorithm for posterior and model inference in MATLAB
Stars: ✭ 123 (-38.81%)
Mutual labels:  bayesian-inference
Libcluster
An extensible C++ library of Hierarchical Bayesian clustering algorithms, such as Bayesian Gaussian mixture models, variational Dirichlet processes, Gaussian latent Dirichlet allocation and more.
Stars: ✭ 129 (-35.82%)
Mutual labels:  bayesian-inference
Statsexpressions
Expressions and dataframes with statistical details 📉 📜🔣✅
Stars: ✭ 144 (-28.36%)
Mutual labels:  bayesian-inference
Tapas
TAPAS - Translational Algorithms for Psychiatry-Advancing Science
Stars: ✭ 121 (-39.8%)
Mutual labels:  bayesian-inference
Zhusuan
A probabilistic programming library for Bayesian deep learning, generative models, based on Tensorflow
Stars: ✭ 2,093 (+941.29%)
Mutual labels:  bayesian-inference
Bcpd
Bayesian Coherent Point Drift (BCPD/BCPD++); Source Code Available
Stars: ✭ 116 (-42.29%)
Mutual labels:  bayesian-inference
Survival Analysis Using Deep Learning
This repository contains morden baysian statistics and deep learning based research articles , software for survival analysis
Stars: ✭ 139 (-30.85%)
Mutual labels:  bayesian-inference
Stan
Stan development repository. The master branch contains the current release. The develop branch contains the latest stable development. See the Developer Process Wiki for details.
Stars: ✭ 2,177 (+983.08%)
Mutual labels:  bayesian-inference
Shinystan
shinystan R package and ShinyStan GUI
Stars: ✭ 172 (-14.43%)
Mutual labels:  bayesian-inference
Rethinking Tensorflow Probability
Statistical Rethinking (2nd Ed) with Tensorflow Probability
Stars: ✭ 152 (-24.38%)
Mutual labels:  bayesian-inference

Bayesian Recurrent Neural Networks

This is a replication of the paper 'Bayesian Recurrent Neural Networks' by Meire Fortunato, Charles Blundell, Oriol Vinyals.

Paper: https://arxiv.org/abs/1704.02798

Status: Basic model replicated.

Requirements

Usage

$ sh download_ptb.sh
$ python bayesian_rnn.py -model medium -log_sigma1 -1.0 -log_sigma2 -7.0 -prior_pi 0.25

To-do:

  • Implement posterior sharpening.
  • Implement image captioning experiment.

Acknowledgements

Thanks to Meire Fortunato for providing the Bayes by Backprop/cell code and @alexkrk for an initial implementation.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].