Modeling of Intellect with the Use of Complex Conditional Reflexes and Selective Neural Network Technologies

Autor: M. Mazurov
Rok vydání: 2019
Předmět:
Zdroj: Advances in Artificial Systems for Medicine and Education II ISBN: 9783030120818
DOI: 10.1007/978-3-030-12082-5_36
Popis: Is considered the mathematical model of the formation of the simplest artificial intelligence on the basis of the creation of difficult conditional reflexes with use of selective neural network technologies. A mathematical model based on complex third-order conditioned reflexes is practically implemented. Is substantiated the possibility of generalization of the mathematical model of artificial intelligence on the basis of the formation of complex conditioned reflexes of any nth order. The mathematical model of the formation of temporary connections at simultaneous inclusion of conditional and unconditional incentives is proved. This justification is based on the hypothesis of the formation of communication channels with each inclusion of conditional and unconditional stimuli and the formation of communication channels between the neural centers of conditional and unconditional stimuli. Are substantiated possible applications in the field of robotics, organization of intellectual speech, translation from foreign languages. Compares some of the theoretical approaches to the modeling of intelligence. A simple model of intelligence based on complex conditioned reflexes, using material devices that are implemented in the brain in the form of certain subsystems, is proposed. These subsystems are: ganglia, cerebellum, hippocampus, neocortex, and other subsystems. The proposed structural scheme of the model of intelligence, including the real material of the device.
Databáze: OpenAIRE