Skip to main content
QUICK REVIEW

[论文解读] Quantum-Inspired Neural Network Model of Optical Illusions

Ivan S. Maksymov|arXiv (Cornell University)|Dec 6, 2023
Neural Networks and Reservoir Computing被引用 4
一句话总结

本文提出一种受量子启发的深度神经网络,利用量子随机数生成器将人类对奈克尔立方体的知觉建模为类似量子比特的知觉状态叠加。该模型表明,知觉切换并非经典的二元交替,而是类似量子的叠加态,与新兴的量子认知理论一致,并在虚拟现实、人工智能训练和神经科学领域具有应用潜力。

ABSTRACT

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 the human's 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 will find applications in video games and virtual reality systems employed for training of astronauts and operators of unmanned aerial vehicles. They will also be 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.

研究动机与目标

  • 开发一种计算模型,准确模拟人类对模糊视觉错觉(特别是奈克尔立方体)的知觉。
  • 探究模糊图形中的知觉切换是否能通过类似量子的叠加态而非经典的二元交替更好地解释。
  • 探索受量子启发的机制(如量子随机数生成和类似量子比特的状态)在模拟人类知觉与决策中的适用性。
  • 提供一个可验证的框架,利用深度学习和来自脑电图及眼动追踪研究的实验数据,验证量子认知理论。
  • 为宇航员和无人飞行器操作员在视觉复杂且模糊的环境中提供训练系统支持。

提出的方法

  • 训练一个深度神经网络,基于视觉输入模式模拟奈克尔立方体的知觉。
  • 使用量子随机数生成器定义网络的连接权重,引入与量子力学原理一致的真实随机性。
  • 将模型的内部状态解释为类似量子比特的叠加态:|ψ⟩ = α|0⟩ + β|1⟩,其中|0⟩和|1⟩代表立方体的两种知觉解释。
  • 应用投影测量算符 M₀ = |0⟩⟨0| 和 M₁ = |1⟩⟨1| 以模拟知觉状态的坍缩,其概率分别为 P(|0⟩) = |α|² 和 P(|1⟩) = |β|²。
  • 将网络的动力学与来自脑电图和眼动追踪研究的实证数据进行验证,显示知觉状态之间持续振荡。
  • 将该模型与最近提出的光学错觉量子振荡器模型进行比较,结果一致预测了叠加态。
Figure 1: (a) The Necker cube. The answer to the question ‘Is the shaded face of the cube at the front or at the rear?’ will change suddenly depending on the observer’s perception, giving rise to a series of rectangular pulses corresponding to the front, $|0\rangle$ , and rear, $|1\rangle$ , percept
Figure 1: (a) The Necker cube. The answer to the question ‘Is the shaded face of the cube at the front or at the rear?’ will change suddenly depending on the observer’s perception, giving rise to a series of rectangular pulses corresponding to the front, $|0\rangle$ , and rear, $|1\rangle$ , percept

实验结果

研究问题

  • RQ1基于量子随机数生成的深度神经网络能否准确模拟人类对奈克尔立方体等模糊视觉错觉的知觉?
  • RQ2奈克尔立方体的知觉状态更应被描述为经典二元切换,还是量子叠加态?
  • RQ3知觉切换的时间动力学在多大程度上与受量子启发模型的预测一致?
  • RQ4受量子启发的神经网络在模糊视觉环境中如何改善宇航员和无人飞行器操作员的训练系统?
  • RQ5该模型能否作为人类知觉与决策中量子认知理论的计算测试平台?

主要发现

  • 该神经网络模型成功将奈克尔立方体的知觉切换模拟为两种知觉状态的类似量子比特的叠加态,而非经典的二元交替。
  • 该模型的输出与实证数据一致,显示知觉状态之间持续振荡,与脑电图和眼动追踪实验中的观察结果相符。
  • 在定义网络权重时使用量子随机数生成器,使知觉动力学与量子测量理论保持一致。
  • 该模型的预测与近期提出的光学错觉量子振荡器模型一致,强化了受量子启发方法的有效性。
  • 该模型表明,知觉状态并非孤立存在,而是处于相干叠加态,支持量子认知假说。
  • 该模型已通过GitHub公开,可供人工智能、神经科学和心理学领域的研究人员复现与拓展。
Figure 2: (a) Projective measurement of a qubit. (b) Projective qubit-like measurement applied to the Necker cube. The two-dimensional shadows of the cubes are identical and perceived by an observer as an ambiguous Necker cube. Considering the shadows as a qubit-like superposition of $|0\rangle$ and
Figure 2: (a) Projective measurement of a qubit. (b) Projective qubit-like measurement applied to the Necker cube. The two-dimensional shadows of the cubes are identical and perceived by an observer as an ambiguous Necker cube. Considering the shadows as a qubit-like superposition of $|0\rangle$ and

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。