On the explainability of quantum neural networks based on variational quantum circuits

• URL: http://arxiv.org/abs/2301.05549v3
• Date: Wed, 23 Oct 2024 10:31:03 GMT
• Title: On the explainability of quantum neural networks based on variational quantum circuits
• Authors: Ammar Daskin,
• Abstract summary: Ridge functions are used to describe and study the lower bound of the approximation done by the neural networks. We show that quantum neural networks based on variational quantum circuits can be written as a linear combination of ridge functions.
• Score: 0.0
• License:
• Abstract: Ridge functions are used to describe and study the lower bound of the approximation done by the neural networks which can be written as a linear combination of activation functions. If the activation functions are also ridge functions, these networks are called explainable neural networks. In this brief paper, we first show that quantum neural networks which are based on variational quantum circuits can be written as a linear combination of ridge functions by following matrix notations. Consequently, we show that the interpretability and explainability of such quantum neural networks can be directly considered and studied as an approximation with the linear combination of ridge functions.

Related papers

• Hysteresis and Self-Oscillations in an Artificial Memristive Quantum Neuron [79.16635054977068]
  We study an artificial neuron circuit containing a quantum memristor in the presence of relaxation and dephasing. We demonstrate that this physical principle enables hysteretic behavior of the current-voltage characteristics of the quantum device.
  arXiv  Detail & Related papers  (2024-05-01T16:47:23Z)
• Information-driven Nonlinear Quantum Neuron [0.0]
  In this study, a hardware-efficient quantum neural network operating as an open quantum system is proposed. We show that this dissipative model based on repeated interactions, which allows for easy parametrization of input quantum information, exhibits differentiable, non-linear activation functions.
  arXiv  Detail & Related papers  (2023-07-18T07:12:08Z)
• Permutation Equivariant Neural Functionals [92.0667671999604]
  This work studies the design of neural networks that can process the weights or gradients of other neural networks. We focus on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order. In our experiments, we find that permutation equivariant neural functionals are effective on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-02-27T18:52:38Z)
• A linear response framework for simulating bosonic and fermionic correlation functions illustrated on quantum computers [58.720142291102135]
  Lehmann formalism for obtaining response functions in linear response has no direct link to experiment. Within the context of quantum computing, we make the experiment an inextricable part of the quantum simulation. We show that both bosonic and fermionic Green's functions can be obtained, and apply these ideas to the study of a charge-density-wave material.
  arXiv  Detail & Related papers  (2023-02-20T19:01:02Z)
• Realization of a quantum neural network using repeat-until-success circuits in a superconducting quantum processor [0.0]
  In this paper, we use repeat-until-success circuits enabled by real-time control-flow feedback to realize quantum neurons with non-linear activation functions. As an example, we construct a minimal feedforward quantum neural network capable of learning all 2-to-1-bit Boolean functions. This model is shown to perform non-linear classification and effectively learns from multiple copies of a single training state consisting of the maximal superposition of all inputs.
  arXiv  Detail & Related papers  (2022-12-21T03:26:32Z)
• Parametrized constant-depth quantum neuron [56.51261027148046]
  We propose a framework that builds quantum neurons based on kernel machines. We present here a neuron that applies a tensor-product feature mapping to an exponentially larger space. It turns out that parametrization allows the proposed neuron to optimally fit underlying patterns that the existing neuron cannot fit.
  arXiv  Detail & Related papers  (2022-02-25T04:57:41Z)
• 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)
• Quantifying scrambling in quantum neural networks [0.0]
  We characterize a quantum neural network's error in terms of the network's scrambling properties via the out-of-time-ordered correlator. Our results pave the way for the exploration of quantum chaos in quantum neural networks.
  arXiv  Detail & Related papers  (2021-12-02T17:28:17Z)
• Development and Training of Quantum Neural Networks, Based on the Principles of Grover's Algorithm [0.0]
  This paper proposes the concept of combining the training process of a neural network with the functional structure of that neural network, interpreted as a quantum circuit. As a simple example of a neural network, to showcase the concept, a perceptron with one trainable parameter - the weight of a synapse connected to a hidden neuron.
  arXiv  Detail & Related papers  (2021-10-01T14:08:43Z)
• 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)
• Entanglement Classification via Neural Network Quantum States [58.720142291102135]
  In this paper we combine machine-learning tools and the theory of quantum entanglement to perform entanglement classification for multipartite qubit systems in pure states. We use a parameterisation of quantum systems using artificial neural networks in a restricted Boltzmann machine (RBM) architecture, known as Neural Network Quantum States (NNS)
  arXiv  Detail & Related papers  (2019-12-31T07:40:23Z)

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.