It might change in the future, but there are few reasons to have only four categories up to date. It is a crude measure to separate all the great projects, but gives you a rough idea of what a project might be.
Today, the fifth category, Model, is added. Models are the realizations of mathematical concepts and research activities, and they represent how data should be consumed to train computers. They act like seeds with which you can evolve your own idea, and are different from the projects in the existing categories.
The Model category will include any model or neural network based on Theano, Torch, Caffe, and TensorFlow. Hope you enjoy the new category and watch how it grows.
Apache UIMA DUCC
UIMA DUCC is a Linux cluster controller designed to scale out any UIMA pipeline for high throughput collection processing jobs as well as for low latency real-tme applications
CNTK, the Computational Network Toolkit by Microsoft Research, is a unified deep-learning toolkit that describes neural networks as a series of computational steps via a directed graph
Tuktu is a big data analytics platform that focuses on ease of use
Disco is a lightweight, open-source framework for distributed computing based on the MapReduce paradigm
Hydra is a distributed data processing and storage system originally developed at AddThis
Pretty Tensor provides a high level builder API for TensorFlow
Meteor is an operator-oriented, extensible query language, which uses a Json-like data model to support applications that analyze semi and unstructured data
A distributed system designed to ingest and process time series data
Theano implementation of Tree RNNs aka Recursive Neural Networks
Convolutional Neural Network for Text Classification in Tensorflow
Subscribe for upcoming posts!
Join the channel!