On the possible Computational Power of the Human Mind

TL;DR

This paper explores whether artificial neural networks can model the computational power of the human mind, analyzing their relationship and potential in capturing human cognitive capabilities based on recent neural network research.

Contribution

It proposes a framework to characterize the human mind's power through neural network computational complexity and discusses the relevance of neural networks as models of human cognition.

Findings

Neural networks can approximate certain cognitive functions.

Computational complexity offers a way to compare mind and machine.

Recent results support neural networks as models of human mental processes.

Abstract

The aim of this paper is to address the question: Can an artificial neural network (ANN) model be used as a possible characterization of the power of the human mind? We will discuss what might be the relationship between such a model and its natural counterpart. A possible characterization of the different power capabilities of the mind is suggested in terms of the information contained (in its computational complexity) or achievable by it. Such characterization takes advantage of recent results based on natural neural networks (NNN) and the computational power of arbitrary artificial neural networks (ANN). The possible acceptance of neural networks as the model of the human mind's operation makes the aforementioned quite relevant.