Search Results for "software development using ai" - Page 5

We present BudgetedSVM, a C++ toolbox containing highly optimized implementations of three recently proposed algorithms for scalable training of Support Vector Machine (SVM) approximators: Adaptive Multi-hyperplane Machines (AMM), Budgeted Stochastic Gradient Descent (BSGD), and Low-rank Linearization SVM (LLSVM). BudgetedSVM trains models with accuracy comparable to LibSVM in time comparable to LibLinear, as it allows solving highly non-linear classification problems with millions of...

A proximity forest is a data structure that allows for efficient computation of approximate nearest neighbors of arbitrary data elements in a metric space. See: O'Hara and Draper, "Are You Using the Right Approximate Nearest Neighbor Algorithm?", WACV 2013 (best student paper award). One application of a ProximityForest is given in the following CVPR publication: Stephen O'Hara and Bruce A. Draper, "Scalable Action Recognition with a Subspace Forest," IEEE Conference on Computer...

This project develops a simple, fast and easy to use Python graph library using NumPy, Scipy and PySparse.

Code of this library is partialy based on myCNN MATLAB class written by Nikolay Chemurin.

The Mars Rover Simulator project is based on the evolutionary robotics paradigm where an artificial agent acquires its skills through the process of artificial evolution. This simulator can be useful to evolve neural network controllers for the rover

The aim of ALIVE is to develop new approaches to the engineering of flexible, adaptable distributed service-oriented systems based on the adaptation of social coordination and organisation mechanisms.

Program to performing the complete cycle of neural networks analysis: preparing data, choosing neural network (CasCor, MP, LogRegression, PNN), learning of network, monitoring learning state, ROC-analysis, optimization of network parameters using GA.

Computer System for Adaptive Intelligent Life :: seeks to create a software system that is capable of learning. The project's ultimate goal is to further the ability of software to both adapt to individual users, and to respond their needs.

Blunder is an automated tool for analyzing chained exceptions in Java. It's usefull for classify, generate a customized error message and a list for possible solutions.

This is implementation of parallel genetic algorithm with "ring" insular topology. Algorithm provides a dynamic choice of genetic operators in the evolution of. The library supports the 26 genetic operators. This is cross-platform GA written in С++.

ANT is a lightweight implementation in C of a kind of artificial neural net called Multilayer Perceptron, which uses the backpropagation algorithm as learning method. The package includes an introductory example to start using artificial neural nets.