LibTopoART provides C# implementations of several TopoART neural networks which are suited to problems such as online-learning, lifelong learning from data streams, as well as incremental learning and prediction from non-stationary data, noisy data, imbalanced data, and incomplete data.
Get Started
$ dotnet add package LibTopoARTReadme
LibTopoART
LibTopoART provides implementations of several neural networks based on the TopoART architecture. This architecture has been developed as a unified machine learning approach tackling frequent problems arising in cognitive robotics and advanced machine learning, such as online-learning, lifelong learning from data streams, as well as incremental learning and prediction from non-stationary data, noisy data, imbalanced data, and incomplete data.
Besides the TopoART neural network itself, LibTopoART comprises implementations of Episodic TopoART (episodic clustering of data streams), Hypersphere TopoART (clustering and topology-learning), TopoART-AM (associative memory), TopoART-C and Hypersphere TopoART-C (classification), and TopoART-R (regression).
The reference manual, samples, and visualisation tools can be downloaded from the LibTopoART website.