Quantum-tunnelling deep neural network for optical illusion recognition
This work addresses the challenge of improving neural network performance on perceptual tasks like optical illusion recognition, which is incremental as it builds on existing DNN and quantum-inspired methods.
The authors tackled the problem of recognizing optical illusions by introducing a quantum-tunnelling deep neural network (QT-DNN) that processes information using quantum tunnelling effects, demonstrating its ability to simulate human perception of illusions like the Necker cube and Rubin's vase with arguments for superiority over traditional activation functions.
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.