Projects

Natural Language Toolkit (NLTK)

NLTK — the Natural Language Toolkit — is a suite of open source Python modules, linguistic data and documentation for research and development in natural language processing, supporting dozens of NLP tasks, with distributions for Windows, Mac OSX and Linux.

WEKA

Weka is a collection of machine learning algorithms for solving real-world data mining problems. It is written in Java and runs on almost any platform. The algorithms can either be applied directly to a dataset or called from your own Java code.

RapidMiner (YALE): Java Data Mining

RapidMiner (formerly YALE) is the most comprehensive open-source software for intelligent data analysis, data mining, knowledge discovery, machine learning, predictive analytics, forecasting, and analytics in business intelligence (BI). RapidMiner provides more than 400 data mining operators, a ... [More] graphical user interface (GUI), an online tutorial with hands-on data mining applications, a comprehensive PDF tutorial, many visualization schemes for data sets and data mining results, many different learning and meta-learning schemes ranging from decision tree and rule learners to neural networks, SVMs, ensemble methods, etc. RapidMiner is implemented in Java and available under GPL (GNU General Public License) as well as under a developer license (OEM license) for closed-source developers [Less]

PyMVPA

Python module to ease pattern classification analyses of large datasets. It provides high-level abstraction of typical processing steps (e.g. data preparation, classification, feature selection, generalization testing), a number of implementations of some popular algorithms (e.g. kNN, Ridge ... [More] Regressions, Sparse Multinomial Logistic Regression, GPR. RFE, I-RELIEF), and bindings to external ML libraries (libsvm, shogun, R). While it is not limited to neuroimaging data (e.g. FMRI) it is eminently suited for such datasets. [Less]

OpenCog Framework

The Open Cognition Framework (OpenCog) is software for the collaborative development of safe and beneficial Artificial General Intelligence. OpenCog provides research scientists and software developers with a common platform to build and share artificial intelligence programs. Programs written ... [More] or adapted for OpenCog may be combined and used in concert with one another for experimentation or to achieve better results compared to their stand-alone counterparts. OpenCog is under active development, but doesn't yet have a official release. It is currently best suited for machine learning developers, but have an interest in making more accessible to new comers. [Less]

Mastrave

Mastrave is a free software library written to perform vectorized scientific computing and to be as compatible as possible with both GNU Octave and Matlab computing frameworks, offering general purpose, portable and freely available features for the scientific community. Mastrave is mostly oriented ... [More] to ease complex modelling tasks such as those typically needed within environmental models, even when involving irregular and heterogeneous data series. . Semantic array programming The Mastrave project attempts to allow a more effective, quick interoperability between GNU Octave and Matlab users by using a reasonably well documented wrap around the main incompatibilities between those computing environments and by promoting a reasonably general idiom based on their common, stable syntagms. It also promotes the systematic adoption of data-transformation abstractions and lightweight semantic constraints to enable concise and reliable implementations of models following the paradigm of semantic array programming. There are a couple of underlying ideas: library design is language design and vice versa (Bell labs); language notation is definitely a "tool of thought" (Iverson), in the sense that there is a feedback between programming/mathematical notation and the ability to think new scientific insights. And perhaps ethic ones. . Science and society Mastrave is free software, which is software respecting your freedom. As many other free scientific software packages, it is offered to the scientific community to also promote the development of a free society more concerned about cooperation rather than competitiveness, heading toward knowledge and culture freedom. Such a vision implies the possibility for motivated individuals to freely access, review and contribute even to the cutting-edge academic culture. This possibility relies on the development of tools and methodologies helping to overcome economic, organizational and institutional barriers (i.e. knowledge oligopolies) while systematically promoting reproducible research. This is a long-term goal to which the free software paradigm can and has been able to actively cooperate. Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011 Daniele de Rigo Verbatim copying and distribution of this entire article is permitted in any medium without royalty provided this notice is preserved. [Less]

rl-glue

RL-Glue is both a set of ideas and standards, as well as a software implementation provided through this site. In theory, RL-Glue is a set of common guidelines for all RL researchers to follow to allow researchers to share and compare agents and environments with greater ease. The software ... [More] implementation of RL-Glue is the reusable glue to connect the basic parts of an experiment. RL-Glue is functionally a test harness to "plug in" agents and environments and experiment without having to continually rewrite the connecting code. As of RL-Glue 2.0, connecting agents and environments and experiments over a network is now supported. [Less]

Treex - NLP Framework

Treex (formerly TectoMT) is a highly modular NLP software system implemented in Perl programming language under Linux. It is primarily aimed at Machine Translation, making use of the ideas and technology created during the Prague Dependency Treebank project. At the same time, it is also hoped to ... [More] significantly facilitate and accelerate development of software solutions of many other NLP tasks, especially due to re-usability of the numerous integrated processing modules (called blocks), which are equipped with uniform object-oriented interfaces. [Less]

rl-viz

RL-Viz provides the reinforcement learning community for the first time ever with a flexible, general, standardized, cross language and cross platform protocol/framework for managing and visualizing the interaction between agents and environments in reinforcement learning experiments. RL-Viz is a ... [More] protocol and library written on top of RL-Glue, a proposed standard communication protocol for reinforcement learning. RL-Viz is a project layered over RL-Glue. RL-Viz supports advanced features of environments and agents and run-time loading of agents and environments. RL-Viz is being used as the foundation for the Reinforcement Learning Competition 2008, culminating in an event at the International Conference on Machine Learning 2008. RL-Viz is heavily used in the RL-Library Project. [Less]

rl-library

The reinforcement learning library is a library of agents, environment, and experiments that are compatible with RL-Glue and potentially RL-Viz.