Search Results for "artificial intelligence" - Page 7

pyDATR is an implementation of the DATR language written in Python and usable as Python library. It provides a means for persistence and some extensability with Python functions.

This is a Python package for general Bayesian inference.

General purpose agents using reinforcement learning. Combines radial basis functions, temporal difference learning, planning, uncertainty estimations, and curiosity. Intended to be an out-of-the-box solution for roboticists and game developers.

pystats is a comprehensive Python module implementing algorithms for statistics and information theory, including probability distributions, descriptive statistics, analysis of variance, regression, and inference.

Robotic Manipulator Development and Simulation Environment in Python and Blender. IMPORTANT: Development moved to github. http://github.com/ajnsit/r2d3

Software to fit whole-sentence language models using the principle of maximum entropy. For developers of speech recognizers, text prediction interfaces, OCR, machine translation software.

Educational game framework supporting board games, strategy games, and other grid-based game boards. Currently uses Python/wxPython as the application language/library. C++ libs included to help create AI for the various games.

A.I. security app. Development ceased.

A Python interface to the Wordnet database of word meanings and lexical relationships. allows the user to type expressions such as N['dog'], hyponyms(N['dog'][0]), and closure(ADJ['red'], SYNONYM) to query the database for lexical relationships.

Net.py is a tool for learning about neural nets. Currently, it only allows the user to experiment with a Hopfield net. I am now extending it to cover the Kohonen net. I'd be pleased to receive suggestions and criticism.

RISO: distributed, heterogeneous Bayesian belief networks. Belief network: a probability model defined on an acyclic directed graph; distributed: nodes can be on different hosts; and heterogeneous: allowing different types of conditional distributions.

VFML -- Very Fast Machine Learning toolkit. A collection of tools, learners, and APIs for working with high-speed data streams and very large data sets.

The Genetic Architecture Framework is intended to explore and experiment with artificial life techniques using a genetic base for the physical and neural networks for the brain, in a game based simulated world.

HORUS is a system for knowledge acquisition, hypothesis generation, inference and learning. It is an interactive, internet environment accessible to a diverse community of users (public-access or membership basis) - see also UMKAILASH project for more.

Charlemagne is a versatile genetic programming application which includes a command-line client and an interactive console mode. It features built in input-output mapping support, and is user-extensible for complex fitness evaluation in Python and Lisp

Galileo is a library for developing custom distributed genetic algorithms developed in Python. It provides a robust set of objects that can be used directly or as the basis of derived objects. Its modularity makes it easy to extend the functionality. The

jrgp is a strong-typed Genetic Programming system, which features a graphical interface (gool) to setup and run GP-problems and a tool (fs-d) that greatly simplifies the definition of a GP-problem.

Chloe - a chatterbot with charisma. Learns from experience, and speaks any language you teach her. Perhaps even useful, but surely entertaining.

The Python Genetic Programming Project implements a Genetic Programming System a la J Koza in Python.

pySPACE is a modular software for processing of large data streams that has been specifically designed to enable distributed execution and empirical evaluation of signal processing chains. Various signal processing algorithms (so called nodes) are available within the software, from finite impulse response filters over data-dependent spatial filters (e.g. CSP, xDAWN) to established classifiers (e.g. SVM, LDA). pySPACE incorporates the concept of node and node chains of the MDP framework. Due...

Project to Design and Implement a new programming language. The language is named Hybrid (c), as it's nature. We "build on" existing languages (Python & others), and not start from scratch (as C++ builds on C). see Docs.

Cellicone is a project to develop an artificial life organism with the necessary components to make it comparable to biological life as we know it. This includes components ranging from proteins to cells to organs to limbs, and many steps between.

aVolve is an evolutionary/genetic algorithm designed to evolve single-cell organisms in a micro ecosystem. It currently uses the JGAP Genetic algorithm, but does include a primitive genetic algorithm written in Python.

a distributed engine for abstract neural network development via natural-language programming

nBoost is a suite of boosting algorithms designed to solve binary classification problems on data that is not linearly separable by a convex combination of base hypotheses, i.e. noisy data. WARNING: Active development. Underlying algorithm is unstable.