Search Results for "artificial intelligence python" - Page 3

Content-based Image Retrieval (CBIR) consists of retrieving visually similar images to a given query image from a database of images. It is done by comparing selected visual features such as color, texture and shape from the image database.

This project applies an interpretation of a k-NN algorithm to a library of GPS commuter data for speed prediction. The overall goal is to lay the foundation for a power management protocol for use in electric vehicles with hybrid energy storage.

An adaptive neural network and evolutionary algorithms approach to the machine learning tasks, based on the modular graph grammars. Tested on the "two spirals problem" and other tasks. Implemented in Matlab and C++.

An implementation of a new proposed model of smoothly spiking neural networks + a fully analytical gradient descent algorithm.

This project contains code for evaluation of reflection symmetry detection algorithms

A MATLAB spectral clustering package to handle large data sets (200,000 RCV1 data) on a 4GB memory general machine. We implement various ways of approximating the dense similarity matrix, including nearest neighbors and the Nystrom method.

A graphical MatLab framework for estimating the parameters of, modeling and simulating static and dynamic linear and polynomial systems in the errors-in-variables context with the intent of comparing various estimation strategies.

Overhead Imagery Research Data Set (OIRDS) - an annotated data library & tools to aid in the development of computer vision algorithms

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.

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

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.

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...