Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments

• URL: http://arxiv.org/abs/2309.07056v2
• Date: Wed, 4 Oct 2023 18:57:50 GMT
• Title: Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments
• Authors: Tareq Jaouni, S\"oren Arlt, Carlos Ruiz-Gonzalez, Ebrahim Karimi, Xuemei Gu, Mario Krenn
• Abstract summary: We use a technique called $inception$ or $deep$ $dreaming$ to explore what neural networks learn about quantum optics experiments. Our story begins by training deep neural networks on the properties of quantum systems. We find that the network can shift the initial distribution of properties of the quantum system, and we can conceptualize the learned strategies of the neural network.
• Score: 0.5242869847419834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their promise to facilitate new scientific discoveries, the opaqueness of neural networks presents a challenge in interpreting the logic behind their findings. Here, we use a eXplainable-AI (XAI) technique called $inception$ or $deep$ $dreaming$, which has been invented in machine learning for computer vision. We use this technique to explore what neural networks learn about quantum optics experiments. Our story begins by training deep neural networks on the properties of quantum systems. Once trained, we "invert" the neural network -- effectively asking how it imagines a quantum system with a specific property, and how it would continuously modify the quantum system to change a property. We find that the network can shift the initial distribution of properties of the quantum system, and we can conceptualize the learned strategies of the neural network. Interestingly, we find that, in the first layers, the neural network identifies simple properties, while in the deeper ones, it can identify complex quantum structures and even quantum entanglement. This is in reminiscence of long-understood properties known in computer vision, which we now identify in a complex natural science task. Our approach could be useful in a more interpretable way to develop new advanced AI-based scientific discovery techniques in quantum physics.

Related papers

• CTRQNets & LQNets: Continuous Time Recurrent and Liquid Quantum Neural Networks [76.53016529061821]
  Liquid Quantum Neural Network (LQNet) and Continuous Time Recurrent Quantum Neural Network (CTRQNet) developed. LQNet and CTRQNet achieve accuracy increases as high as 40% on CIFAR 10 through binary classification.
  arXiv  Detail & Related papers  (2024-08-28T00:56:03Z)
• A Quick Introduction to Quantum Machine Learning for Non-Practitioners [0.0]
  The paper covers basic quantum mechanics principles, including superposition, phase space, and entanglement. It also reviews classical deep learning concepts, such as artificial neural networks, gradient descent, and backpropagation. An example problem demonstrates the potential advantages of quantum neural networks.
  arXiv  Detail & Related papers  (2024-02-22T16:48:17Z)
• VIOLET: Visual Analytics for Explainable Quantum Neural Networks [6.3356849928129]
  VIOLET is a novel visual analytics approach to improve the explainability of quantum neural networks. We develop three visualization views: Ansatz View, Feature View and satellite chart. We evaluate VIOLET through two case studies and in-depth interviews with 12 domain experts.
  arXiv  Detail & Related papers  (2023-12-23T15:06:43Z)
• ShadowNet for Data-Centric Quantum System Learning [188.683909185536]
  We propose a data-centric learning paradigm combining the strength of neural-network protocols and classical shadows. Capitalizing on the generalization power of neural networks, this paradigm can be trained offline and excel at predicting previously unseen systems. We present the instantiation of our paradigm in quantum state tomography and direct fidelity estimation tasks and conduct numerical analysis up to 60 qubits.
  arXiv  Detail & Related papers  (2023-08-22T09:11:53Z)
• On the Interpretability of Quantum Neural Networks [0.0]
  Interpretability of artificial intelligence (AI) methods, particularly deep neural networks, is of great interest. Here, we explore the interpretability of quantum neural networks using local model-agnostic interpretability measures commonly utilized for classical neural networks. A feature of our explanations is the delineation of the region in which data samples have been given a random label, likely subjects of inherently random quantum measurements.
  arXiv  Detail & Related papers  (2023-08-22T00:43:14Z)
• Quantum activation functions for quantum neural networks [0.0]
  We show how to approximate any analytic function to any required accuracy without the need to measure the states encoding the information. Our results recast the science of artificial neural networks in the architecture of gate-model quantum computers.
  arXiv  Detail & Related papers  (2022-01-10T23:55:49Z)
• A quantum algorithm for training wide and deep classical neural networks [72.2614468437919]
  We show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We numerically demonstrate that the MNIST image dataset satisfies such conditions. We provide empirical evidence for $O(log n)$ training of a convolutional neural network with pooling.
  arXiv  Detail & Related papers  (2021-07-19T23:41:03Z)
• On quantum neural networks [91.3755431537592]
  We argue that the concept of a quantum neural network should be defined in terms of its most general function. Our reasoning is based on the use of the Feynman path integral formulation in quantum mechanics.
  arXiv  Detail & Related papers  (2021-04-12T18:30:30Z)
• The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning [84.33745072274942]
  We show how to represent linear and non-linear layers as unitary quantum gates, and interpret the fundamental excitations of the quantum model as particles. On top of opening a new perspective and techniques for studying neural networks, the quantum formulation is well suited for optical quantum computing.
  arXiv  Detail & Related papers  (2021-03-08T17:24:29Z)
• The power of quantum neural networks [3.327474729829121]
  In the near-term, however, the benefits of quantum machine learning are not so clear. We use tools from information geometry to define a notion of expressibility for quantum and classical models. We show that quantum neural networks are able to achieve a significantly better effective dimension than comparable classical neural networks.
  arXiv  Detail & Related papers  (2020-10-30T18:13:32Z)
• Quantum Deformed Neural Networks [83.71196337378022]
  We develop a new quantum neural network layer designed to run efficiently on a quantum computer. It can be simulated on a classical computer when restricted in the way it entangles input states.
  arXiv  Detail & Related papers  (2020-10-21T09:46:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.