Quantum-tunnelling deep neural network for optical illusion recognition

TL;DR

This paper introduces a quantum-tunnelling inspired deep neural network that effectively recognizes optical illusions, demonstrating potential advantages over traditional activation functions and aligning with biological and quantum information processing principles.

Contribution

The paper presents a novel QT-based DNN architecture for optical illusion recognition, highlighting its superiority and biological relevance compared to existing models.

Findings

QT-DNN successfully recognizes optical illusions like humans.

QT-based activation functions outperform traditional ones.

The model aligns with biology-inspired and quantum information principles.

Abstract

The discovery of the quantum tunnelling (QT) effect -- the transmission of particles through a high potential barrier -- was one of the most impressive achievements of quantum mechanics made in the 1920s. Responding to the contemporary challenges, I introduce a deep neural network (DNN) architecture that processes information using the effect of QT. I demonstrate the ability of QT-DNN to recognise optical illusions like a human. Tasking QT-DNN to simulate human perception of the Necker cube and Rubin's vase, I provide arguments in favour of the superiority of QT-based activation functions over the activation functions optimised for modern applications in machine vision, also showing that, at the fundamental level, QT-DNN is closely related to biology-inspired DNNs and models based on the principles of quantum information processing.