Search Results for "offline artificial intelligence\" - Page 4

The project goal is to develop several IP cores that would implement artificial neural networks using FPGA resources. These cores will be designed in such a way to allow easy integration in the Xilinx EDK framework.

QASE is a Java-based API designed to provide all the functionality needed to create game agents in Quake 2. Powerful enough to facilitate high-end research, it is also suitable for undergrad courses geared towards classic AI and agent-based systems.

A simulator for learning techniques for dynamic bayesian networks.

Linear Time Invariant (LTI) system identification using particle swarm optimization (PSO) algorithm. Creators : Vahid Kiani, Hadi Sadoghi Yazdi

A scientific enterprise to try to learn basic patterns using directed acyclic graphs.

MILT is designed to facilitate research in imitation learning through first-person computer games. Featuring strategic, tactical and reactive modules, it allows developers to work with their preferred games or take advantage of integrated Quake2 support.

Bayesian Surprise Matlab toolkit is a basic toolkit for computing Bayesian surprise values given a large set of input samples. It is also useful as way of exploring surprise theory. For more information see also: http://ilab.usc.edu/

The simpleSVM project contains Machine Learning codes for algorithms based on the SimpleSVM. It provides methods for Support Vector Machines and related methods, such as One-Clas SVM, nu-SVM...

Matlab Classification Toolbox contains implementations of the following classifiers: Naive Bayes, Gaussian, Gaussian Mixture Model, Decision Tree and Neural Networks. This toolbox allows users to compare classifiers across various data sets.

NodeWeaver is a tool for generating SystemML Neuronal Networks from Neuronal Network descriptions (these technologies are nascent, so no links yet...). Intended use is to generate SystemML NNs for later execution using a SystemML simulator (e.g. BRAHMS).

Design and develop Recommendation and Adaptive Prediction Engines to address eCommerce opportunities. Build a portfolio of engines by creating and porting algorithms from multiple disciplines to a usable form. Try to solve NetFlix and other challenges.

This project consists in matlab scripts to create and train an Elman network. The task assigned to the network is to transform the orthographic form of a verb presented in the infinitive into its past participle and vice versa M.Carastro & R.Scanavino

neuro fuzzy net: 1. Object oriented Programming! 2. matlab project with back propagation, and hibrid learning. 3. Can use to MLP or ANFIS Sugeno modelling. 4. Integrated with Simulink (Sfunction M) by any questions mail me : tsepkovsky@yandex.ru

The purpose of this project is to implement a java program that can show/edit Neural Network objects made in matlab.

Esta é a documentação de um projeto de conclusão de curso feito na conclusão do curso de Engenharia de Computação-UNIVALI.É um conjunto de arquivos C e Matlab contendo a implementação da Lógica Fuzzy e simulações em sistema de enegia.

A collection of Matlab functions and scripts for computing the saliency map for an image, for determining the extent of a proto-object, and for serially scanning the image with the focus of attention.

mlearn is a gradient based learning toolbox for matlab. While it is fairly simple to build a neural network, it is designed for ease of implementing new kind of gradient based architecture.

URBI: Universal Robotic Body Interface. URBI is a scripted command language used to control robots (AIBO, pioneer,...). It is a robot-independant API based on a client/server architecture. Liburbi C++/Java/Matlab are available here. Forum available at ht

MPT is a toolbox that supplies cross-platform libraries for real-time perception primitives, including face detection, eye detection, blink detection, and color tracking.

Function 1. classifier_knn 2. accuracy_knn Description 1. Returns the estimated label of one test instance, the k nearest training instances, the k nearest training labels and creates a chart circulating the nearest training instances (chart 2-D of the first two features of each instance). 2. Returns the estimated labels of one or multiple test instances and the accuracy of the estimates.

This is a MATLAB toolbox implementing Computer Vision and Pattern Recognition related algorithms. Check out http://cvprtoolbox.svn.sourceforge.net/svnroot/cvprtoolbox/. See also http://note.sonots.com/SciSoftware.html

Matlab and Octave code to fit a mixture of Gaussians with covariance regularization to data using EM update rules.

Human action classification using a spatio-temporal maximum average correlation height filter.

Land Mines detection using Image Processing

GURLS - (Grand Unified Regularized Least Squares) is a software package for training multiclass classifiers based on the Regularized Least Squares (RLS) loss function. The initial version has been designed and implemented in Matlab. Teh current goal is to implement an object-oriented C++ version to allow for a wider distribution of the library within the open-source developers' comunity. Main functionalities already implemented are: * Automatic parameter selection. * Handle...