Research tool for interactive training of artificial neural networks.
BNNS is a research tool for interactive training of artificial neural networks based on the Response Function Plots visualization method. It enables users to simulate, visualize and interact in the learning process of a Multi-Layer Perceptron on tasks which have a 2D character. Tasks like the famous two-spirals task or classification of satellite image data.
MESH is a tool that measures distortion between two discrete surfaces (triangular meshes) using the Hausdorff distance to compute a maximum, mean and root-mean-square errors between two given surfaces. It also displays the error values on the surface.