TY - JOUR ID - 21814 TI - Extending concepts of mapping of human brain to artificial intelligence and neural networks JO - Scientia Iranica JA - SCI LA - en SN - 1026-3098 AU - Joghataie, A. AD - Department of Civil Engineering, Structural Engineering Group, Sharif University of Technology, Tehran, Iran Y1 - 2021 PY - 2021 VL - 28 IS - Special issue on collective behavior of nonlinear dynamical networks SP - 1529 EP - 1534 KW - neural networks KW - Artificial intelligence KW - Homunculus KW - AIculus KW - NNculus KW - autonomous robots DO - 10.24200/sci.2020.53714.3378 N2 - The concept of Homunculus from human neurophysiology is extended to artificially intelligent systems. It is assumed that an artificially intelligent processing system behaves similar to a minicolumn or ganglion in the natural animal brain, where in general there is a layer of afferent (input) neurons, a number of interconnecting processing cells, and a layer of efferent (output) neurons or organs. The objective is to identify the correlation between the stimulus to each afferent neuron and the corresponding response from each efferent organ when the intelligent system is subjected to its expected stimuli. To illustrate the general concept a small 3-layered feedforward neural network is used as a simple example and a NNculus is built. Building NN and AI culi for autonomous robots can be used in their design and for performance quality control. Another useful application is in studying the topographic organization in internal layers of the minicolumns of human brain through hardware or numerical simulations. UR - https://scientiairanica.sharif.edu/article_21814.html L1 - https://scientiairanica.sharif.edu/article_21814_fcb7bc19aa0e6c0debbc16e983e70ed4.pdf ER -