• List of public services including text, image and general purpose services

Google COLAB ofers an access to an virual machine which can be access via web browser with the syntax similar to JupyterNotebook. For details see

• Google Colab
• Introduction to Google colab

• Weka - free Java tool with many implemented models (also feature selection, classifiers combiners etc.)
• RapidMiner - Also written in Java tools for creating comlex data mining models with nice and simple GUI. It implements models of Weka and LibSVM - some details are avaliable in here
  • Radoop - Interface to Mohout and Hadoop based on RapidMiner visualization engine - acquired by RapidMiner
  • DeepLearning in RM
  • RapidMiner Developers FAQ
• Apache Mahout - Large Scale Distributed Data Mining
• Joone- Java Object Oriented Neural Engine
• MULAN A java based tool with Weka for multi-label learning problems
• ENCOG - Encog Artificial Intelligence Framework for Java
  • Heat Onr Rsearch - Documentation and books on Encog
  • Intro how to combine RapidMiner and Python
• knime - Data mining tool with visual data flow designer, comprehensive to Weka and RapidMiner
• Keel - Data mining tool also with visual data flow designer, with an aim on instance selection, fuzzy systems and evolutionary computing
• Gate - text mining tool
• ELKI - Environment for Developing KDD-Applications Supported by Index-Structures - DM tool with optimized for large datasets by the application of Index-structures
• DeepLearning4J - Deep Learning for Java
  • ND4J
• SMILE - Smile - Statistical Machine Intelligence and Learning Engine - nice and simple ML libraries for Java with JupytherNotebook support

Overview of machine learning tools in Python

• Scikit learn
• PyBrain - Reinforcement Learning, Artificial Intelligence and Neural Network Library.
• MLPy
• PyML
• LibSVM
• cuDNN - Cuda Deep Neural Network implementation by NVidia
  • Caffe - further extension to cuDNN

Stream learning

• Scikit multiflow - stream learning

Python tools:

• NLTK - Natural Language Toolkit
• Oython libraries - a set of precompiled libraries for Windows

• LibSVM - a very good library of different SVM implementations by Chih-Chung Chang and Chih-Jen Lin. All the tools are avaliable here
• SVM Light - a large set of algorithms of SVM'a by Thorsten Joachims. It includs more complex versions of SVM:
  • SVM struct - Different of SVMs able to learn structured output
• List of software

• Ghost Miner - (licenced) very good and fast tools developed by KIS UMK in Toruń (Poland), distributed by Fujitsu (company FQS)
• Intemi - new projest (also KIS UMK in Toruń) currently under development
• Spider - my favourite Matlab toolbox (for free), it itegrate many other matlab, C and Java packages like LibSVM, Weka etc. I'm also developing this project and all my AddIns can be downloaded from here (in case of any problems please contact me on email).
• R-project in an open-source statistical programming language
• MLOSS project - repository of machine learning open source software
• Elefant - Machine learning project written in Python
• GPML - Gaussian Processes for Machine Learning Matlab & Octave Toolbox
• Oger - a Python toolbox for rapidly building, training and evaluating modular learning architectures on large datasets.

• SNAP - Graph analysis software developed on Stanford - C++ libraries + Python interface (SNAPY)

I did a simple comparison between Weka, RapidMiner and Knime - I did a model with 100 fold CV on dataset with a few thousands samples with 5NN classifier. Obtained results proofed that weka is the fastest tool (few seconds) Rapid Miner required few minutes, and Knime was the slowest (a few minutes). I've also compared it with Matlab Spider - I won't comment that results :).

• BIRT - Eclipse based reporting tool
• Pentaho - Pentaho BI tool with all in one including DM (Weka), ETL, Reporting.
• Jasper - Reporting tool written mostly in Java but also in C++ and PHP
• SpagoBI - Spago tool for BI

• cuDNN - NVidia release of Machine Learning library supporting deep learning
• cuda-convnet - a fast C++/CUDA implementation of convolutional neural networks
• Deep Learn Toolbox - Matlab/Octave toolbox for deep learning.
• PyLearn2 - a library for deep learning in python