Accord.NET Framework Portable was designed as an extension to AForge.NET, another framework for processing scientific applications.
Accord.NET Framework Portable provides users with statistical analysis, machine learning, image processing and computer vision methods for .NET applications.
What's New in This Release:
General:
· Working on more source code examples for the documentation.
Accord.Math:
· Adding Levenshtein distance for strings.
Accord.Imaging:
· Updating BagOfVisualWords to be fully serializable.
Accord.MachineLearning:
· Adding K-dimensional trees (K-d trees);
· Adding Mean-Shift clustering algorithm;
· Adding support for weights in Gaussian Mixture Models;
· Correcting the name of the K-Nearest Neighbors algorithm;
· Improving K-Nearest Neighbors for double[] using a K-d tree;
· Changing K-Nearest Neighbors generic argument to represent the
· instance type rather than the type of the array of instances.
Accord.Statistics:
· Adding interfaces for density estimation kernels;
· Adding Gaussian, Epanechnikov, Uniform density kernels;
· Adding Bartlett's and Levene's tests for variances;
· Adding hypothesis tests for comparing ROC curves;
· Adding support for scatterplot generation directly from ROC curves;
· Adding running Markov models and running Markov classifier filters;
· Adding stoch...