Neuro-Skins: Dynamics, Plasticity and Effect of Neuron Type and Cell Size on Their Response

Joghataie, Abdolreza; Dizaji, Mehrdad Shafiei

doi:10.1007/s11063-018-9795-7

Cited by 1 publication

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The interconnecting neurons as well as the output organs issue their action potentials based on the sigmoidal function y=2/(1+e -cz ) -1, where c is the characteristic constant of the neuron or organ, z is the weighted sum of all its inputs, and y is the action potential issued by the neuron or organ. This type of sigmoidal neuron has been widely used by many researchers including the author of this article [19,20].…”

Section: A Simple Example Problem Of Building a Nn-culusmentioning

confidence: 99%

Extending Concepts of Mapping of Human Brain to Artificial Intelligence and Neural Networks

Joghataie

2020

Scientia Iranica

Self Cite

View full text Add to dashboard Cite

This paper introduces the concept of mapping of artificially intelligent (AI) computational systems. The concept of Homunculus from human neurophysiology is extended to AI systems. It is assumed that an AI system behaves similar to a mini-column or ganglion in the natural animal brain, comprised of 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 stimuli. To illustrate the general concept a small 3-layered feedforward Neural Network (NN) is used as a simple example and a NNculus is built. An important application is in the quality control of autonomous robots where an NN or AI culi can be built to evaluate its performance. Another useful application is in studying the topographic organization in the internal layers of the mini-columns of the human brain through hardware or numerical simulations using artificial neural networks.

show abstract

Section: A Simple Example Problem Of Building a Nn-culusmentioning

confidence: 99%