Training single-electron and single-photon stochastic physical neural networks

• URL: http://arxiv.org/abs/2604.10861v1
• Date: Sun, 12 Apr 2026 23:57:03 GMT
• Title: Training single-electron and single-photon stochastic physical neural networks
• Abstract summary: One alternative is physical neural networks (PNNs), in which learning and inference are performed directly via physical processes.<n>PNNs arise when underlying neurons are realized by the dynamics of an activation switch.<n>We show that when empirical outputs are used in the backward pass, the network achieves more than 97% test accuracy with few trials per layer.
• Score: 0.48757691171453793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The computational demands of deep learning motivate the investigation of alternative approaches to computation. One alternative is physical neural networks~(PNNs), in which learning and inference are performed directly via physical processes. Stochastic PNNs arise when the underlying neurons are realized by the dynamics of a stochastic activation switch. Here we propose novel electronic and photonic stochastic neurons. The electronic realization is implemented by single-electron tunneling through a quantum dot. The photonic realization is implemented via a single-photon source driving one of two modes coupled via a controllable beam-splitter-like interaction. In the electronic case, the charge state of the quantum dot forms the basis for the stochastic neuron, whereas in the photonic case the occupation of the undriven mode serves as the basis for the stochastic neuron. Training of stochastic PNNs is performed with models of stochastic neurons, as well as with coherently-driven, single-photon detector stochastic neurons previously introduced. Several training strategies for MNIST handwritten digit classification have been investigated using single-hidden-layer stochastic PNNs, including varying the number of trials in each layer to control forward pass stochasticity and employing either true probability or empirical outputs in the backward pass to evaluate their influence on gradient estimation. We show that when empirical outputs are used in the backward pass, the network achieves more than 97\% test accuracy with few trials per layer. Despite the simplicity of the model architecture, high test accuracy is maintained in the presence of a high degree of noise and model uncertainty. The results demonstrate the potential of embracing stochastic PNNs for deep learning.

Related papers

• Fractional Spike Differential Equations Neural Network with Efficient Adjoint Parameters Training [63.3991315762955]
  Spiking Neural Networks (SNNs) draw inspiration from biological neurons to create realistic models for brain-like computation.<n>Most existing SNNs assume a single time constant for neuronal membrane voltage dynamics, modeled by first-order ordinary differential equations (ODEs) with Markovian characteristics.<n>We propose the Fractional SPIKE Differential Equation neural network (fspikeDE), which captures long-term dependencies in membrane voltage and spike trains through fractional-order dynamics.
  arXiv  Detail & Related papers  (2025-07-22T18:20:56Z)
• Experiment on creating a neural network with weights determined by the potential of a simulated electrostatic field [0.0]
  This paper explores the possibility of determining the weights and thresholds of a neural network using the potential.<n>The electrostatic field is simulated in the Builder C++ environment.<n>The effectiveness of the resulting neural network is evaluated using the MNIST test dataset.
  arXiv  Detail & Related papers  (2025-06-26T14:26:38Z)
• 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)
• Quantum-limited stochastic optical neural networks operating at a few quanta per activation [6.12660587056967]
  Energy efficiency in computation is ultimately limited by noise, with quantum limits setting the fundamental noise floor.<n>We study optical neural networks where all layers except the last are operated in the limit that each neuron can be activated by just a single photon.<n>We show that by using a physics-based probabilistic model of the neuron activations in training, it is possible to perform accurate machine-learning inference in spite of the extremely high shot noise.
  arXiv  Detail & Related papers  (2023-07-28T17:59:46Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits [61.94533459151743]
  This work addresses the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks.
  arXiv  Detail & Related papers  (2023-03-30T02:40:28Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks [56.35403810762512]
  Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware. We study spike-based implicit differentiation on the equilibrium state (SPIDE) that extends the recently proposed training method.
  arXiv  Detail & Related papers  (2023-02-01T04:22:59Z)
• Toward Physically Realizable Quantum Neural Networks [15.018259942339446]
  Current solutions for quantum neural networks (QNNs) pose challenges concerning their scalability. The exponential state space of QNNs poses challenges for the scalability of training procedures. This paper presents a new model for QNNs that relies on band-limited Fourier expansions of transfer functions of quantum perceptrons.
  arXiv  Detail & Related papers  (2022-03-22T23:03:32Z)
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks [68.8204255655161]
  Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks. We explore the diversity of the neurons within the hidden layer during the learning process. We analyze how the diversity of the neurons affects predictions of the model.
  arXiv  Detail & Related papers  (2021-09-20T15:12:16Z)
• Recurrent Quantum Neural Networks [7.6146285961466]
  Recurrent neural networks are the foundation of many sequence-to-sequence models in machine learning. We construct a quantum recurrent neural network (QRNN) with demonstrable performance on non-trivial tasks. We evaluate the QRNN on MNIST classification, both by feeding the QRNN each image pixel-by-pixel; and by utilising modern data augmentation as preprocessing step.
  arXiv  Detail & Related papers  (2020-06-25T17:59:44Z)
• Stochasticity in Neural ODEs: An Empirical Study [68.8204255655161]
  Regularization of neural networks (e.g. dropout) is a widespread technique in deep learning that allows for better generalization. We show that data augmentation during the training improves the performance of both deterministic and versions of the same model. However, the improvements obtained by the data augmentation completely eliminate the empirical regularization gains, making the performance of neural ODE and neural SDE negligible.
  arXiv  Detail & Related papers  (2020-02-22T22:12:56Z)

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.