English»Software»Machine Learning»Toolkits/Frameworks | searchivarius.org
log in | about 

Graph-based frameworks

Sequence-to-sequence toolkits


Apache Mahout   - Mahout
Dask   - a flexible parallel computing library for analytic computing.
dask-ml   - parallel and distributed machine learning using Dask alongside existing machine learning libraries like Scikit-Learn: 1) accelerating existing algorithms within Scikit-Learn 2) Implementing new parallel algorithms 3) Deploying other distributed services like XGBoost or TensorFlow.
Dlib   - a modern C toolkit containing machine learning algorithms and tools for creating complex software in C .
FACTORIE   - is a toolkit for deployable probabilistic modeling, implemented as a software library in Scala. It provides its users with a succinct language for creating relational factor graphs, estimating parameters and performing inference.
KeyStone   - a software framework, written in Scala, from the UC Berkeley AMPLab designed to simplify the construction of large scale, end-to-end, machine learning pipelines with Apache Spark.
Kubeflow   - an open, community driven project to make it easy to deploy and manage an ML stack on Kubernetes.
LEARNSC   - SVM, NN and FL MATLAB based user-friendly routines.
MeTA  a modern C++ data science toolkit
Microsoft DMTK   - Distributed Machine Learning Tookit
MLlib   - Apache Spark's scalable machine learning library.
mlpack   - is an intuitive, fast, scalable C++ machine learning library, meant to be a machine learning analog to LAPACK. It aims to implement a wide array of machine learning methods and functions as a "swiss army knife" for machine learning researchers.
Netlab   - Matlab toolbox including Gaussian Process Regression, Mixture models and Neural Networks.
OpenCV (Open Source Computer Vision)   - is a library of programming functions for real time computer vision. It includes a statistical learning software for several methods, including naive Bayes, SVM, and gradient boosting.
PaddlePaddle   - (PArallel Distributed Deep LEarning) is an easy-to-use, efficient, flexible and scalable deep learning platform, which is originally developed by Baidu scientists and engineers for the purpose of applying deep learning to many products at Baidu.
Photon-ML   - A scalable machine learning library on Apache Spark (by LinkedIn)
QuickNet   - QuickNet is a suite of software that facilitates the use of multi-layer perceptrons (MLPs) in statistical pattern recognition systems. It is primarily designed for use in speech processing but may be useful in other areas.
Ray  system for parallel and distributed Python that unifies the ML ecosystem.
ScalaNLP   - a suite of machine learning and numerical computing libraries.
scikit-learn   - machine learning in Python.
statnet   - a suite of software packages for network analysis that implement recent advances in the statistical modeling of networks.
Suite of Fast Incremental Algorithms for Machine Learning.  
TADM The Toolkit for Advanced Discriminative Modeling  
The Kernel-Machine Library: Software and Tutorials for ML  
TMVA Toolkit for Multivariate Data Analysis with ROOT   - Supports several ML algorithms including SVM, (boosted) decision trees, and neural networks.
torch   - is a scientific computing framework with wide support for machine learning algorithms. It is easy to use and provides a very efficient implementation, thanks to an easy and fast scripting language, LuaJIT, and an underlying C implementation.
TorchCraft   - an interface between StarCraft: Brood War and Torch, the deep learning environment.
TorchGPipe   - A GPipe implementation in PyTorch
Turi Create   - Apple's framework to simplify development of custom ML models.
Vowpal Wabbit   - Fast machine learning
WEKA   - Weka (Waikato Environment for Knowledge Analysis) is a popular package of machine learning and data mining software written in Java, developed at the University of Waikato. WEKA is free software available under the GNU General Public License.