Resumen
This paper describes a new neural network able to adapt itself, both its parameters and its structure, to a data set in real-time conditions. The adaptation is based on a non-supervised learning procedure. The new neural network can automatically create interconnections between neurons using a Gaussian activation function. Still another important feature of this new neural network is the use of few neurons to make a good prediction using a reduced number of examples. This is relevant in order to make fast calculations using few resources in real-time applications. Some examples focusing on mobile robotics applications are included in order to demonstrate its good performance.
