Neural networks
Fully-connected Network

Fully connected MLP

Default neural network architecture in visual editor is a fully connected multi-layer perceptron (MLP).

"Fully connected" means that each neuron in each layer within the neural network applies a linear transformation to the input vector through a weights matrix. As a result, all possible connections layer-to-layer are present, meaning every input of the input vector influences every output of the output vector.

Fully-connected neural network (MLP) architecture, pre-selected at first inside Neural network node within visual editor, has 6 layers, each containing 512 perceptrons, and uses the "swish" (also known as SiLU) activation function. All these parameters - e.g., the number of layers, the number of perceptrons in each layer, and the activation function to use for each layer - are user configurable. Default values are known to work, though they might not be optimal for your specific problem.