Neural network structures: current and future states

Abstract

Two prevailing points of view on the way of creating artificial intelligence have been presented: based on the consistent patterns the evolution of neurons of the natural nervous system went through and based on radically new patterns, different from the consistent patterns seen in the natural evolution, shall be used to develop neural network structures and programs. The main structural elements of the future artificial intelligence based on the laws of the development of human neural networks have been presented: the main types of neurotransmitters and their role in the modulation of informative signals; a principle of diffuse transmission of information through the intercellular matrix; a concept of improving efficiency of functioning neural network structures based on diffuse transmission of signals in the form of hormones, growth factors, cytokines. It was pointed out that the researchers who are aiming at the development of artificial intelligence must remember about potential negative consequences that should be taken into account and avoided at the stages of problem semantic comprehension.