Quantum-Cognitive Neural Networks: Assessing Confidence and Uncertainty with Human Decision-Making Simulations

TL;DR

This paper explores quantum-tunnelling neural networks inspired by human cognition to classify images, aiming to emulate human decision-making and assess confidence and uncertainty in AI outputs.

Contribution

It introduces QT-NNs combined with quantum cognition theory as a novel approach to mimic human perception and improve decision-making in machine learning.

Findings

QT-NNs can replicate human-like decision processes

QT-NNs outperform traditional ML algorithms in classification tasks

The model provides insights into confidence and uncertainty assessment

Abstract

Modern machine learning (ML) systems excel in recognising and classifying images with remarkable accuracy. However, like many computer software systems, they can fail by generating confusing or erroneous outputs or by deferring to human operators to interpret the results and make final decisions. In this paper, we employ the recently proposed quantum-tunnelling neural networks (QT-NNs), inspired by human brain processes, alongside quantum cognition theory, to classify image datasets while emulating human perception and judgment. Our findings suggest that the QT-NN model provides compelling evidence of its potential to replicate human-like decision-making and outperform traditional ML algorithms.