Weekly Machine Learning OpenSource Roundup – Nov. 9, 2017

Capsule Net by Geoffrey Hinton, Sara Sabour and Nicholas Frosst is published, and many implementations on various frameworks are also published in this week.

For a concise roundup, the implementation from Gram.AI and an adversarial attack scenario by @jaesik817 are listed.


AirBnB Dataset Analysis
Prediction of where a new AirBnB user will book his first Destination

AirSim with openAI gym and keras-rl integration for autonomous copter RL

Example of android app written in Qt/Qml which uses MXNet for plant image recognition.

A Neural Conversational Model
A neural chatbot using sequence to sequence model with attentional decoder implements by Tensorflow 1.4 (Estimator, Experiment, Dataset)

A collection of python Machine Learning articles and examples. You will find code related to Reinforcement Learning, Q Learning, MDP, Bellman, OpenAI solutions and others

Deep Architecture Genealogy
Deep Learning Architecture Genealogy Project

A Real-time Mario Kart AI using CNNs, Offline Search, and DAGGER


A flexible, scalable deep probabilistic programming library built on PyTorch.

Typed frontend to TensorFlow and higher-order deep learning

OpenNMT TensorFlow
A general purpose sequence modeling tool in TensorFlow with production in mind.

Explore high-dimensional datasets and how your algo handles specific regions.

GAN Playground
Experiment with Generative Adversarial Nets in your browser. An introduction to GANs.


Dynamic Routing Between Capsules
A PyTorch implementation of the NIPS 2017 paper “Dynamic Routing Between Capsules”.

Adversarial Attack to Capsule Networks
Tensorflow Implementation of Adversarial Attack to Capsule Networks

Radio Transformer Networks
A PyTorch implementation of Radio Transformer Networks from the paper “An Introduction to Deep Learning for the Physical Layer”.

Alpha Pooling
Code for our paper “Generalized Orderless Pooling Performs Implicit Salient Matching” published at ICCV 2017.

Progressive Growing of GANs
Torch implementation of “Progressive Growing of GANSs for Improved Quality, Stability, and Variation”


Pretrained models for Pytorch
Pretrained ConvNets for pytorch: ResNeXt101, ResNet152, InceptionV4, InceptionResnetV2, etc.

High level network definitions with pre-trained weights in TensorFlow

AI inference library based on mbed and TensorFlow

Deep Learning based Python Library for Stock Market Prediction and Modelling


Looking into adding your repo? tweet to @stkim1!

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s