Artificial Intelligence

When computers become capable of "natural thinking," should we begin to teach them like children?

Research on symbolic and numerical approaches to machine learning, first order logic, intelligent document processing, spatial data mining, human-computer interaction.

Research on higher-order concept learning, inductive logic programming, multi-agent learning systems, integration of prior knowledge, induction and deduction, incremental learning, hybrid symbolic/connectionist approaches, evolutionary strategies.

An algorithm that incrementally constructs decision trees from labeled examples. [AFL]

A general purpose library for Bayesian filtering written in C++. [LGPL]

Computational model of human language acquisition written in Java; currently acquires a protolanguage of nouns and verbs language based on visual perception. [BSD]

Software for counting and analyzing word n-grams in text. This package provides standard tests of association for identifying word n-grams in large corpora and allows users to implement other tests with minimal scripting knowledge. Written in Perl. [GPL]

A suite of Java libraries for the linguistic analysis of human language which can link entity mentions to database entries, uncover relations, cluster documents, and discover significant trends. [GPL]

A community effort listing of reproducible research via open source software, open access to data and results, and open standards for interchange. [FREE]

A fast graph clustering software that computes normalized cut and ratio association for a given undirected graph without any eigenvector computation.

Statistical servers LibLinear and SVM-light, two fast loading models for supervised classification. Also MetaPixel GUI, a front end for MetaPixel using Mono/C#. [GPL]

A Javascript implementation of Joseph Weizenbaum's Eliza by Arne Solli.

Focuses on creating genuine Artificial Intelligence - the technology that enables machines to converse with humans in natural language. Based on a groundbreaking approach, Ai's technology will pass the Turing Test for machine intelligence by 2011.

A seasoned humorous greeter and site Admin. Auto-responses, humor and key word laughter and site resources.

Contains various chatterbots, chatrooms, news and papers.

AI Dreams - A place to talk about artificial intelligence, technology, robotics, films, graphics

Turing's original 1950 article on machine intelligence, where he introduces the famous Turing Test, and started this profound multi-decade debate.

Provider of application development services, software systems, and licensor of the Holographic/Quantum Neural Technology (HNeT).

Sells software implementations of feedforward and recurrent networks trained with backpropagation and feature maps.

Consulting design of neurocomputing hardware, Neuromorphic aVLSI bus infrastructure, support for wet lab research.

Unsupervised learning, PCA, ICA, SOM, statistical pattern recognition, image and signal analysis.

Unsupervised learning, machine learning, computational models of neural processing.

Vision, Bayesian methods, neural computation.

Automated Analysis of ECG.

Particle filtering and Monte Carlo Markov Chain methods.

Visual perception, machine vision, image processing.

Research in artificial neural networks, pattern recognition and signal processing.

A platform for simulating complex neural systems.

MS Excel add-ins based on neural networks. Designed for predicting, classification and financial forecasting.

Neural network software for Windows with numeric, text and image functions.

Icon-based neural network development software. Supports several types of networks and training algorithms. Trial version is available.

Appears in Journal of Machine Learning Research. 2003.

Developers of software for computer animation and special effects industry. Products do automatic camera motion recovery, and foreground subtraction. Site has regular news updates.

By Andrew Tomlinson