The video shows the work of a Grasshopper component in C# which performs the reinterpretation of input vectors into output vectors according to previously defined training samples. It uses a classic backpropagation network. The network structure can be defined by providing inputs for number and type of network layers, the number of neurons in each layer, a learning rate and the number of training cycles to be run previously to the actual input vector translation.
The core library "NeuronDotNet 3.0" was written by Vijeth Dinesha
For more info about Neural networks go to:
Raúl Rojas: Theorie der Neuronalen Netze. Eine systematische Einführung. 4. korrigierter Nachdruck. Springer, Berlin u. a. 1996, ISBN 3-540-56353-9 (Springer-Lehrbuch).