Fermi-Dirac machines as quantizations of neurons

• URL: http://arxiv.org/abs/2605.24386v1
• Date: Sat, 23 May 2026 04:09:03 GMT
• Title: Fermi-Dirac machines as quantizations of neurons
• Abstract summary: We reinterpret Fermi-Dirac machines as canonical quantizations of classical neurons.<n>We develop efficient hybrid quantum-classical algorithms for evaluating outputs and gradients of our quantized neurons.<n> Numerical experiments indicate that neurons based on quantum Hamiltonians can learn functions that classical neurons cannot.
• Score: 51.809748057605184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fermi-Dirac machines were proposed recently as an approach to solving semidefinite optimization problems on quantum computers. Here, we reinterpret them as canonical quantizations of classical neurons. By viewing a classical neuron as an activation function applied to a parameterized classical Hamiltonian, we quantize this model by replacing classical variables with operators whose eigenvalues encode their possible values. This follows the standard approach to canonical quantization in quantum mechanics. Crucially, when the Hamiltonian consists of commuting operators, our construction reduces exactly to a classical neuron. More generally, our approach yields an activation observable, defined as an activation function applied to a parameterized quantum Hamiltonian. The output of this quantized neuron is a random variable with expectation value equal to that of the activation observable with respect to an input state. We develop efficient hybrid quantum-classical algorithms for evaluating outputs and gradients of our quantized neurons, enabling evaluation and training. These algorithms rely on basic primitives that include random sampling, Hamiltonian simulation, and the Hadamard test. We also quantize a whole host of other activation functions, including the smooth rectified linear unit (ReLU), sigmoid linear unit, Gaussian-smoothed ReLU, and Gaussian error linear unit (GeLU), which are known to be useful for deep learning applications. Numerical experiments indicate that neurons based on quantum Hamiltonians can learn functions that classical neurons cannot. We further define a computational decision problem based on Fermi-Dirac neurons and prove that it is BQP-complete, providing complexity-theoretic evidence against efficient classical simulation. Finally, we generalize our approach to continuous quantum variables and sketch two different ways of composing these neurons into networks.

Related papers

• Canonical quantization of neurons [51.809748057605184]
  We apply canonical quantization to a fundamental computational primitive of machine learning: the neuron.<n>We develop hybrid quantum-classical algorithms for training and evaluation.<n>Our work establishes canonical quantization as a principled framework for constructing quantum machine learning primitives.
  arXiv  Detail & Related papers  (2026-07-06T12:39:06Z)
• Simulating Quantum Many-Body States with Neural-Network Exponential Ansatz [0.0]
  We develop a surrogate neural network solver that generates the exponential ansatz parameters using the Hamiltonian parameters as inputs. We illustrate the effectiveness of this approach by training neural networks of several quantum many-body systems.
  arXiv  Detail & Related papers  (2024-11-12T15:48:23Z)
• Non-binary artificial neuron with phase variation implemented on a quantum computer [0.0]
  We introduce an algorithm that generalizes the binary model manipulating the phase of complex numbers. We propose, test, and implement a neuron model that works with continuous values in a quantum computer.
  arXiv  Detail & Related papers  (2024-10-30T18:18:53Z)
• Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems [77.88054335119074]
  We use FNOs to model the evolution of random quantum spin systems. We apply FNOs to a compact set of Hamiltonian observables instead of the entire $2n$ quantum wavefunction.
  arXiv  Detail & Related papers  (2024-09-05T07:18:09Z)
• Quantum-Assisted Hilbert-Space Gaussian Process Regression [0.0]
  We propose a space approximation-based quantum algorithm for Gaussian process regression. Our method consists of a combination of classical basis function expansion with quantum computing techniques.
  arXiv  Detail & Related papers  (2024-02-01T12:13:35Z)
• 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)
• 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)
• Variational Monte Carlo calculations of $\mathbf{A\leq 4}$ nuclei with an artificial neural-network correlator ansatz [62.997667081978825]
  We introduce a neural-network quantum state ansatz to model the ground-state wave function of light nuclei. We compute the binding energies and point-nucleon densities of $Aleq 4$ nuclei as emerging from a leading-order pionless effective field theory Hamiltonian.
  arXiv  Detail & Related papers  (2020-07-28T14:52:28Z)

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.