Engineering nonlinear activation functions for all-optical neural networks via quantum interference

• URL: http://arxiv.org/abs/2504.04009v2
• Date: Wed, 16 Jul 2025 04:30:59 GMT
• Title: Engineering nonlinear activation functions for all-optical neural networks via quantum interference
• Authors: Ruben Canora, Xinzhe Xu, Ziqi Niu, Hadiseh Alaeian, Shengwang Du,
• Abstract summary: All-optical neural networks (AONNs) promise transformative gains in speed and energy efficiency for artificial intelligence (AI)<n>We present a low-power nonlinear activation scheme based on a three-level quantum system driven by dual laser fields.<n>These results mark a major advance toward scalable, high-speed, and energy-efficient optical AI hardware.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: All-optical neural networks (AONNs) promise transformative gains in speed and energy efficiency for artificial intelligence (AI) by leveraging the intrinsic parallelism and wave nature of light. However, their scalability has been fundamentally limited by the high power requirements of conventional nonlinear optical elements. Here, we present a low-power nonlinear activation scheme based on a three-level quantum system driven by dual laser fields. This platform introduces a two-channel nonlinear activation matrix with both self- and cross-nonlinearities, enabling true multi-input, multi-output optical processing. The system supports tunable activation behaviors, including sigmoid and ReLU functions, at ultralow power levels (17 uW per neuron). We validate our approach through theoretical modeling and experimental demonstration in rubidium vapor cells, showing the feasibility of scaling to deep AONNs with millions of neurons operating under 20 W of total optical power. Crucially, we also demonstrate the all-optical generation of gradient-like signals with backpropagation, paving the way for all optical training. These results mark a major advance toward scalable, high-speed, and energy-efficient optical AI hardware.

Related papers

• Experimental neuromorphic computing based on quantum memristor [0.2618499987393917]
  We show how the memristive feedback loop enhances the nonlinearity and hence the performance of the tested algorithms.<n>In these cases, we highlight the essential role of the quantum memristive element and demonstrate the possibility of using it as a building block in more sophisticated networks.
  arXiv  Detail & Related papers  (2025-04-25T21:03:19Z)
• Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment [48.90869997343841]
  We experimentally implement a versatile and scalable training algorithm, called direct feedback alignment, on a hybrid electronic-photonic platform.<n>An optical processing unit performs large-scale random matrix multiplications, at speeds up to 1500 TeraOPS under 30 Watts of power.<n>We study the scaling of the training time, and demonstrate a potential advantage of our hybrid opto-electronic approach for ultra-deep and wide neural networks.
  arXiv  Detail & Related papers  (2024-09-01T12:48:47Z)
• Training Large-Scale Optical Neural Networks with Two-Pass Forward Propagation [0.0]
  This paper addresses the limitations in Optical Neural Networks (ONNs) related to training efficiency, nonlinear function implementation, and large input data processing. We introduce Two-Pass Forward Propagation, a novel training method that avoids specific nonlinear activation functions by modulating and re-entering error with random noise. We propose a new way to implement convolutional neural networks using simple neural networks in integrated optical systems.
  arXiv  Detail & Related papers  (2024-08-15T11:27:01Z)
• Single Neuromorphic Memristor closely Emulates Multiple Synaptic Mechanisms for Energy Efficient Neural Networks [71.79257685917058]
  We demonstrate memristive nano-devices based on SrTiO3 that inherently emulate all these synaptic functions. These memristors operate in a non-filamentary, low conductance regime, which enables stable and energy efficient operation.
  arXiv  Detail & Related papers  (2024-02-26T15:01:54Z)
• Ultrafast second-order nonlinear photonics -- from classical physics to non-Gaussian quantum dynamics [0.0]
  State-of-the-art devices achieve saturated nonlinear interactions with thousands of photons when driven by continuous-wave lasers. Ultrafast pulses may soon push nonlinear optics into the realm of single-photon nonlinearities.
  arXiv  Detail & Related papers  (2024-01-11T21:25:43Z)
• Optical Extreme Learning Machines with Atomic Vapors [0.3069335774032178]
  Extreme learning machines explore nonlinear random projections to perform computing tasks on high-dimensional output spaces. This manuscript explores the possibility of using atomic gases in near-resonant conditions to implement an optical extreme learning machine. Our results suggest that these systems have the potential not only to work as an optical extreme learning machine but also to perform these computations at the few-photon level.
  arXiv  Detail & Related papers  (2024-01-08T10:19:28Z)
• All-optical modulation with single-photons using electron avalanche [66.27103948750306]
  We demonstrate all-optical modulation enabled by electron avalanche process in silicon.<n>Our approach opens the possibility of gigahertz-speed, and potentially even faster, optical switching at the single-photon level.
  arXiv  Detail & Related papers  (2023-12-18T20:14:15Z)
• Non-Hermitian zero mode laser in a nanophotonic trimer [55.41644538483948]
  We report on the direct observation of a lasing zero mode in a non-Hermitian three coupled nanocavity array. We show efficient excitation for nearly equal pump power in the two extreme cavities. The realization of zero mode lasing in large arrays of coupled nanolasers has potential applications in laser-mode engineering.
  arXiv  Detail & Related papers  (2023-02-03T15:21:44Z)
• Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks [12.952987240366781]
  This work proposes a novel device-to-system hardware-software codesign framework, which enables efficient training of Diffractive optical neural networks (DONNs) Gumbel-Softmax is employed to enable differentiable discrete mapping from real-world device parameters into the forward function of DONNs. The results have demonstrated that our proposed framework offers significant advantages over conventional quantization-based methods.
  arXiv  Detail & Related papers  (2022-09-28T17:13:28Z)
• All-Photonic Artificial Neural Network Processor Via Non-linear Optics [0.0]
  We propose an all-photonic artificial neural network processor. Information is encoded in the amplitudes of frequency modes that act as neurons. Our architecture is unique in providing a completely unitary, reversible mode of computation.
  arXiv  Detail & Related papers  (2022-05-17T19:55:30Z)
• Electromagnetically induced transparency in inhomogeneously broadened divacancy defect ensembles in SiC [52.74159341260462]
  Electromagnetically induced transparency (EIT) is a phenomenon that can provide strong and robust interfacing between optical signals and quantum coherence of electronic spins. We show that EIT can be established with high visibility also in this material platform upon careful design of the measurement geometry. Our work provides an understanding of EIT in multi-level systems with significant inhomogeneities, and our considerations are valid for a wide array of defects in semiconductors.
  arXiv  Detail & Related papers  (2022-03-18T11:22:09Z)
• Designing Kerr Interactions for Quantum Information Processing via Counterrotating Terms of Asymmetric Josephson-Junction Loops [68.8204255655161]
  static cavity nonlinearities typically limit the performance of bosonic quantum error-correcting codes. Treating the nonlinearity as a perturbation, we derive effective Hamiltonians using the Schrieffer-Wolff transformation. Results show that a cubic interaction allows to increase the effective rates of both linear and nonlinear operations.
  arXiv  Detail & Related papers  (2021-07-14T15:11:05Z)
• Topologically Protecting Squeezed Light on a Photonic Chip [58.71663911863411]
  Integrated photonics offers an elegant way to increase the nonlinearity by confining light strictly inside the waveguide. We experimentally demonstrate the topologically protected nonlinear process of spontaneous four-wave mixing enabling the generation of squeezed light on a silica chip.
  arXiv  Detail & Related papers  (2021-06-14T13:39:46Z)
• Rapid characterisation of linear-optical networks via PhaseLift [51.03305009278831]
  Integrated photonics offers great phase-stability and can rely on the large scale manufacturability provided by the semiconductor industry. New devices, based on such optical circuits, hold the promise of faster and energy-efficient computations in machine learning applications. We present a novel technique to reconstruct the transfer matrix of linear optical networks.
  arXiv  Detail & Related papers  (2020-10-01T16:04:22Z)
• Efficient trainability of linear optical modules in quantum optical neural networks [0.0]
  We show that coherent light in $m$ modes can be generically compiled efficiently if the total intensity scales sublinearly with $m$. We further demonstrate efficient trainability of $m$ mode linear optical quantum circuits for variational mean field energy estimation of positive quadratic Hamiltonians for input states that do not have energy exponentially vanishing with $m$.
  arXiv  Detail & Related papers  (2020-08-20T19:26:54Z)
• Entanglement generation via power-of-SWAP operations between dynamic electron-spin qubits [62.997667081978825]
  Surface acoustic waves (SAWs) can create moving quantum dots in piezoelectric materials. We show how electron-spin qubits located on dynamic quantum dots can be entangled.
  arXiv  Detail & Related papers  (2020-01-15T19:00:01Z)

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.