GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → bgroenks96 → normalizing-flows

bgroenks96 / normalizing-flows

Licence: MIT license
Implementations of normalizing flows using python and tensorflow

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

data-sciencemachine-learningmachine-learning-algorithmsnormalizing-flows

Projects that are alternatives of or similar to normalizing-flows

RapLyrics-Back
Model training, custom generative function and training for raplyrics.eu - A rap music lyrics generation project
Stars: ✭ 14 (-6.67%)
Mutual labels:  machine-learning-algorithms
Subjective-Answer-Evaluation
Subjective answer evaluation using machine learning. Give your answers at this link ->
Stars: ✭ 22 (+46.67%)
Mutual labels:  machine-learning-algorithms
perceptron
The simplest Perceptron you'll ever see
Stars: ✭ 45 (+200%)
Mutual labels:  machine-learning-algorithms
Intention-Mining-
Intention Mining in Social Networking. It Mines Emotions and polarity for the given keyword . For the keyword it searchers the twitter for the comments and analyzes the results for various events such as Election results, Sports prediction Movie ratings, Breaking news events such as demonetisation and many more. Bayes , Maximum Entropy and Hidde…
Stars: ✭ 19 (+26.67%)
Mutual labels:  machine-learning-algorithms
bonsai-dt
Programmable Decision Tree Framework
Stars: ✭ 34 (+126.67%)
Mutual labels:  machine-learning-algorithms
ExCon
ExCon: Explanation-driven Supervised Contrastive Learning
Stars: ✭ 17 (+13.33%)
Mutual labels:  machine-learning-algorithms
Innovative-Book-Resources
This repository contains books from different topics and perfect enough to give developers a boost in understanding the concepts of Data Science and Artificial Intelligence(other topics are also included but main highlights are these two).
Stars: ✭ 57 (+280%)
Mutual labels:  machine-learning-algorithms
extra-model
Code to run the ExtRA algorithm for unsupervised topic/aspect extraction on English texts.
Stars: ✭ 43 (+186.67%)
Mutual labels:  machine-learning-algorithms
introduction to normalizing flows
Jupyter Notebook corresponding to 'Going with the Flow: An Introduction to Normalizing Flows'
Stars: ✭ 21 (+40%)
Mutual labels:  normalizing-flows
Handwritten-Digits-Classification-Using-KNN-Multiclass Perceptron-SVM
🏆 A Comparative Study on Handwritten Digits Recognition using Classifiers like K-Nearest Neighbours (K-NN), Multiclass Perceptron/Artificial Neural Network (ANN) and Support Vector Machine (SVM) discussing the pros and cons of each algorithm and providing the comparison results in terms of accuracy and efficiecy of each algorithm.
Stars: ✭ 42 (+180%)
Mutual labels:  machine-learning-algorithms
ugtm
ugtm: a Python package for Generative Topographic Mapping
Stars: ✭ 34 (+126.67%)
Mutual labels:  machine-learning-algorithms
ML-For-Beginners
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
Stars: ✭ 40,023 (+266720%)
Mutual labels:  machine-learning-algorithms
online-course-recommendation-system
Built on data from Pluralsight's course API fetched results. Works with model trained with K-means unsupervised clustering algorithm.
Stars: ✭ 31 (+106.67%)
Mutual labels:  machine-learning-algorithms
random-fourier-features
Implementation of random Fourier features for kernel method, like support vector machine and Gaussian process model
Stars: ✭ 50 (+233.33%)
Mutual labels:  machine-learning-algorithms
tensorflow-rbm
Tensorflow implementation of the Restricted Boltzmann Machine
Stars: ✭ 308 (+1953.33%)
Mutual labels:  machine-learning-algorithms
Learn-Machine-Learning-in-3-month
No description or website provided.
Stars: ✭ 35 (+133.33%)
Mutual labels:  machine-learning-algorithms
Clustering-Python
Python Clustering Algorithms
Stars: ✭ 23 (+53.33%)
Mutual labels:  machine-learning-algorithms
calcuMLator
An intelligently dumb calculator that uses machine learning
Stars: ✭ 30 (+100%)
Mutual labels:  machine-learning-algorithms
PROSAC
PROSAC algorithm in python
Stars: ✭ 19 (+26.67%)
Mutual labels:  machine-learning-algorithms
Self-Driving-Car
Implemented a Convolutional Neural Network for end-to-end driving in a simulator using Tensorflow and Keras. The project involves training over 13,000 images in a unity3d simulator to steer the car successfully throughout the track
Stars: ✭ 29 (+93.33%)
Mutual labels:  machine-learning-algorithms
View All Similar Projects ➔

normalizing-flows

Implementations of normalizing flows for variational inference using Python (3.6+) and Tensorflow (2.0+).

flows_visualization

Installation

pip install git+https://github.com/bgroenks96/normalizing-flows

Getting started

Take a look at the intro notebook for a gentle introduction to normalizing flows.

This library currently implements the following flows:

1 Implemented via JointFlowLVM; the flow architecture from the paper is not currently supported. However, Glow can (and possibly should) be used instead.

API overview

The normalizing_flows package currently provides two interfaces for building flow-based models:

  1. Marginal inference (FlowLVM, JointFlowLVM)

  2. Variational autoencoder (GatedConvVAE)

Marginal inference models directly optimize the log-evidence $\log p(x)$ via the inverse transform of the flow. Note that this requires the flow to support bidirectional (forward + inverse) evaluation. The only flow architecture in this package which supports this (currently) is Glow.

VAE inference minimizes the evidence lower bound (ELBO) and thus requires only forward evaluations, $z \rightarrow z'$ (i.e. the inverse need not be tractable). For VAE inference, Planar, Radial, and Triangular Sylvester flows are all supported via FlowLayer (see the intro notebook for an example). In theory, Glow could also be used in a VAE, but this has not been tested and is not currently supported by FlowLayer, which assumes the latent space to be dense and non-spatial.

Exmaple: Planar vs Sylvester flows

t-SNE mapped latent space across 4 flow steps

Planar vs. Sylvester

Future development

Please note that this package was developed for the purposes of the author's own research. As such, it might not be as fully featured or rounded out as other libraries. However, contributions and discussions about new features and flow implementations is both welcome and encouraged!

Additional types flows under consideration for future versions:

  • Orthogonal/Householder Sylvester flows

  • Inverse Autoregressive Flows (Kingma et al, 2016)

  • Neural Autoregressive Flows (Huang et al, 2018)

Currently, this library has no published documentation outside of docstrings in the code. This may change in the future.

Please feel free to create an issue if anything isn't clear or more documentation is needed on specific APIs.

License and use

This library is free and open source software under the MIT license.

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].