A solitary multi-junction VCSEL termed NeuronSEL exhibits NDR and neuronal spiking features including refractoriness and integrate-and-fire dynamics, enabling optical coincidence detection and XOR operations.
Femtojoule per MAC Neuromorphic Photonics: An Energy and Technology Roadmap
9 Pith papers cite this work, alongside 16 external citations. Polarity classification is still indexing.
9
Pith papers citing it
16
external citations · Pith
abstract
This roadmap consolidates recent advances while exploring emerging applications, reflecting the remarkable diversity of hardware platforms, neuromorphic concepts, and implementation philosophies reported in the field. It emphasizes the critical role of cross-disciplinary collaboration in this rapidly evolving field.
citation-role summary
background 1
citation-polarity summary
years
2026 9roles
background 1polarities
background 1representative citing papers
Hybrid optical implementation of equilibrium propagation via spatial photonic Ising machine demonstrated on Wine classification with numerical MNIST evaluation.
Experimental demonstration that self-pulsing microring resonator networks retain fiber sensor perturbation information, reducing required sampling rate by at least one order of magnitude.
TRON demonstrates a trainable and reconfigurable optical neural network that combines multi-scattering media with DMD-based matrix multiplication and performs in-situ optimization plus neural architecture search on the optical hardware itself.
Thin-film lithium niobate modulators implement electro-optic Softmax and Sigmoid alternatives for transformers that maintain competitive accuracy under 4-bit quantization and characterized noise up to 10 GBaud.
Optical random Fourier feature mapping enables approximation of tenth-order polynomials, special functions, neural activations, and high-dimensional softmax in linear silicon photonic hardware.
An experimental 4-channel TSWDM silicon photonic crossbar achieves 0.96 TOPS for hyperdimensional tensor operations with 3.9% average error and 93.3% Iris accuracy at 10-30 GBd.
Hybrid physics-informed data-driven models outperform both pure physics and pure machine-learning models in generalizability and data efficiency across three photonic system benchmarks.
The paper classifies memory mechanisms in integrated photonic systems and their support for neuromorphic architectures in time-dependent signal processing tasks.
citing papers explorer
-
Neuron Surface Emitting Laser (NeuronSEL): Spiking Regimes and Negative Differential Resistance in Solitary Multi-junction VCSELs
A solitary multi-junction VCSEL termed NeuronSEL exhibits NDR and neuronal spiking features including refractoriness and integrate-and-fire dynamics, enabling optical coincidence detection and XOR operations.
-
Optical Implementation of Equilibrium Propagation Using Spatial Photonic Ising Machines
Hybrid optical implementation of equilibrium propagation via spatial photonic Ising machine demonstrated on Wine classification with numerical MNIST evaluation.
-
Self-Pulsing Microring Resonator Networks for Bandwidth-Efficient Event Detection in an Optical Fiber Sensor
Experimental demonstration that self-pulsing microring resonator networks retain fiber sensor perturbation information, reducing required sampling rate by at least one order of magnitude.
-
TRON: Trainable, architecture-reconfigurable random optical neural networks
TRON demonstrates a trainable and reconfigurable optical neural network that combines multi-scattering media with DMD-based matrix multiplication and performs in-situ optimization plus neural architecture search on the optical hardware itself.
-
Integrated electro-optic attention nonlinearities for transformers
Thin-film lithium niobate modulators implement electro-optic Softmax and Sigmoid alternatives for transformers that maintain competitive accuracy under 4-bit quantization and characterized noise up to 10 GBaud.
-
General-Purpose Nonlinear Function Approximation via Linear Integrated Photonics
Optical random Fourier feature mapping enables approximation of tenth-order polynomials, special functions, neural activations, and high-dimensional softmax in linear silicon photonic hardware.
-
On-chip 1 TOPS Hyperdimensional Photonic Tensor Core using a WDM Silicon Photonic Coherent Crossbar
An experimental 4-channel TSWDM silicon photonic crossbar achieves 0.96 TOPS for hyperdimensional tensor operations with 3.9% average error and 93.3% Iris accuracy at 10-30 GBd.
-
Beyond white- and black-box modeling tools in optical communications and optical computing: physics-informed data-driven modeling
Hybrid physics-informed data-driven models outperform both pure physics and pure machine-learning models in generalizability and data efficiency across three photonic system benchmarks.
-
Memory in Integrated Photonic Neural Networks: From Physical Mechanisms to Neuromorphic Architectures
The paper classifies memory mechanisms in integrated photonic systems and their support for neuromorphic architectures in time-dependent signal processing tasks.