Quantum-Inspired Neural Network Model of Optical Illusions

• Published in: Algorithms Vol. 17; no. 1; p. 30
• Main Author: Maksymov, Ivan S.
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-01-2024
• Subjects: Algorithms; Analysis; Artificial intelligence; Artificial neural networks; Astronaut training; Astronauts; Cognition; Computer & video games; deep neural network; Hierarchies; Machine learning; machine vision; Necker cube; Neural networks; optical illusion; Optical illusions; Perception; Psychology; Quantum physics; Qubits (quantum computing); Random numbers; Unmanned aerial vehicles; Video games; Virtual reality; New York; Germany
• ISSN: 1999-4893; 1999-4893
• DOI: 10.3390/a17010030

Ambiguous optical illusions have been a paradigmatic object of fascination, research and inspiration in arts, psychology and video games. However, accurate computational models of perception of ambiguous figures have been elusive. In this paper, we design and train a deep neural network model to simulate human perception of the Necker cube, an ambiguous drawing with several alternating possible interpretations. Defining the weights of the neural network connection using a quantum generator of truly random numbers, in agreement with the emerging concepts of quantum artificial intelligence and quantum cognition, we reveal that the actual perceptual state of the Necker cube is a qubit-like superposition of the two fundamental perceptual states predicted by classical theories. Our results finds applications in video games and virtual reality systems employed for training of astronauts and operators of unmanned aerial vehicles. They are also useful for researchers working in the fields of machine learning and vision, psychology of perception and quantum–mechanical models of human mind and decision making.