OpenAI is a project which is centred around the advancement of Artificial Intelligence. The project itself is geared toward developing specifications for AI and a default implementation for a set of well known AI tools. This is OpenAI's Neural Network release. The software is written in Java and is built in a modular fashion so that new algorithms and learning rules can be created. Configuration and persistence will be done through XML and a CORBA interface is provided for applications that wish to incorporate the technology.
The OpenAI project is centered around the advancement of Artificial Intelligence. It is geared toward developing specifications for AI and a default implementation for a set of well-known AI tools. The genetic algorithm is written in Java and is built in a modular fashion so that new algorithms and evolution rules can be created.
The OpenAI site is centered around an Open Source project and community involving artificial intelligence. The project itself is the creation of a set of tools that are considered to be models of human intelligence or biomimicry. These tools are intended to be integrated into applications or used stand alone for research.
The Pattern Recognition Application Programmer's Interface aims to be a fully-featured, easy-to-use general C++ framework for various pattern recognition tasks, especially image analysis. It features support for many image formats, well-known image analysis methods, classification and feature analysis tools, XML serialization, etc.
Experience-Based Language Acquisition (EBLA) is an open computational framework for visual perception and grounded language acquisition. It can "watch" a series of short videos and acquire a simple language of nouns and verbs corresponding to the objects and object-object relations in those videos. Upon acquiring this protolanguage, it can perform basic scene analysis to generate descriptions of novel videos. While there have been several systems capable of learning object or event labels for videos, this is the first known system to acquire both nouns and verbs using a grounded computer vision system.
Libtextcat is a library with functions that implement the classification technique described in Cavnar & Trenkle, "N-Gram-Based Text Categorization". It was primarily developed for language guessing, a task on which it is known to perform with near- perfect accuracy. Considerable effort went into making this implementation fast and efficient. The language guesser processes over 100 documents/second on a simple PC, which makes it practical for many uses.
Naiban is a complete standalone Java application and an Avalon/Keel framework classification service. It features Naive-Bayes based algorithms, JDBC backed persistance, and support for text and numerics. Naive Bayes learning classifiers have recently gained popularity in their application to the spam vs. ham problem. Naiban provides a learning classifier service to the Avalon/Keel framework, and comes complete with two text classifiers and a simple numeric classifier. It is easily extendable, and provides two persistance mechanisms for storing trained data.