A Generalized Net Model of the Deep Learning Algorithm

Inhalt:
In this paper a generalized net model of the Deep Learning Neural Network Algorithm (DLNNA) is presented. A DLNN is a self-organizing network with the ability to recognize patterns based on the difference of their form. A DLNN is able to correctly identify an image, speech recognition and natural language processing. Self-organization in the DLNN is also realized uncontrollably. Training for self-organizing DLNN takes only a collection of recurring patterns in the recognizable image and does not need the information for categories that include templates. The output producing process is presented by a Generalized net model.