mlsanityData to 7 Oct 2026

Quantum-tunnelling deep neural network for optical illusion recognition

arXiv 2407.11013 ↗First posted 26 Jun 2024cs.LG cs.AI cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 14 of its 108 references that are in the map. First posted on arXiv 26 Jun 2024.

Builds on

14 of 108 references.

References · 14

  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  2. 2024IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Modelscited by 29
  3. 2019Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitonscited by 19
  4. 2023Analogue and Physical Reservoir Computing Using Water Wavescited by 16
  5. 2021Predictive coding feedback results in perceived illusory contours in a recurrent neural networkcited by 10
  6. 2023Quantum-Inspired Neural Network Model of Optical Illusionscited by 7
  7. 2024Reservoir Computing Using Measurement-Controlled Quantum Dynamicscited by 7
  8. 2023The Physics of Preference: Unravelling Imprecision of Human Preferences through Magnetisation Dynamicscited by 5
  9. 2018Learning from Pseudo-Randomness With an Artificial Neural Network - Does God Play Pseudo-Dice?cited by 3
  10. 2018Deep learning improved by biological activation functionscited by 3
  11. 2021Quantum propensities in the brain cortex and free willcited by 3
  12. 2023Causal potency of consciousness in the physical worldcited by 3
2 more
  1. 2024Fake news: No ban, No spread -- with Sequestrationcited by 2
  2. 2022Bistable perception, precision and neuromodulationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2024Quantum-Cognitive Neural Networks: Assessing Confidence and Uncertainty with Human Decision-Making Simulationscited by 4
  2. 2025Full-Precision and Ternarised Neural Networks with Tunnel-Diode Activation Functions: Computing and Physics Perspectivescited by 3
  3. 2025TunnElQNN: A Hybrid Quantum-classical Neural Network for Efficient Learningcited by 2
  4. 2025Transforming Traditional Neural Networks into Neuromorphic Quantum-Cognitive Models: A Tutorial with Applicationscited by 0
  5. 2025Quantum-Cognitive Tunnelling Neural Networks for Military-Civilian Vehicle Classification and Sentiment Analysiscited by 0
  6. 2026Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deploymentcited by 0