Publications (26)
Three dimensional waveguide-interconnects for scalable integration of photonic neural networks
Johnny Moughames, Xavier Porte, Michael Thiel +5
Photonic waveguides are prime candidates for integrated and parallel photonic interconnects. Such interconnects correspond to large-scale vector matrix products, which are at the h…
Two-color optically-addressed spatial light modulator as generic spatio-temporal systems
Vladimir Semenov, Xavier Porte, Ibrahim Abdulhalim +2
Nonlinear spatio-temporal systems are the basis for countless physical phenomena in such diverse fields as ecology, optics, electronics and neuroscience. The canonical approach to…
A complete, parallel and autonomous photonic neural network in a semiconductor multimode laser
Xavier Porte, Anas Skalli, Nasibeh Haghighi +3
Neural networks are one of the disruptive computing concepts of our time. However, they fundamentally differ from classical, algorithmic computing in a number of fundamental aspect…
Spiking Rate and Latency Encoding with Resonant Tunnelling Diode Neuron Circuits and Design Influences
Giovanni Donati, Dafydd Owen-Newns, Joshua Robertson +6
Neuromorphic computing, inspired by the functionality and efficiency of biological neural systems, holds promise for advancing artificial intelligence and computational paradigms.…
Diffractive coupling for photonic networks: how big can we go?
Sheler Maktoobi, Luc Froehly, Louis Andreoli +4
Photonic networks are considered a promising substrate for high-performance future computing systems. Compared to electronics, photonics has significant advantages for a fully para…
Single Pixel Image Classification using an Ultrafast Digital Light Projector
Aisha Kanwal, Graeme E. Johnstone, Fahimeh Dehkhoda +5
Pattern recognition and image classification are essential tasks in machine vision. Autonomous vehicles, for example, require being able to collect the complex information containe…
(3+1)D-printed adiabatic 1-to-N broadband couplers
Adrià Grabulosa, Xavier Porte, Erik Jung +3
We report single-mode 3D optical couplers leveraging adiabatic power transfer towards up to 4 output ports. We use the CMOS compatible additive (3+1)D \emph{flash}-TPP printing for…
Neuron Surface Emitting Laser (NeuronSEL): Spiking Regimes and Negative Differential Resistance in Solitary Multi-junction VCSELs
Maria Duque-Gijon, Joshua Robertson, Dafydd Owen-Newns +6
Neuromorphic photonics is emerging as a powerful platform for fast and efficient optical information processing and sensing. However, future brain-inspired photonic systems require…
On-chip wave chaos for photonic extreme learning
Matthew R. Wilson, Jack A. Smith, Michael J. Strain +1
The increase in demand for scalable and energy efficient artificial neural networks has put the focus on novel hardware solutions. Integrated photonics offers a compact, parallel a…
Fundamental aspects of noise in analog-hardware neural networks
Nadezhda Semenova, Xavier Porte, Louis Andreoli +3
We study and analyze the fundamental aspects of noise propagation in recurrent as well as deep, multi-layer networks. The main focus of our study are neural networks in analogue ha…
Micropillars with a controlled number of site-controlled quantum dots
Arsenty Kaganskiy, Fabian Gericke, Tobias Heuser +3
We report on the realization of micropillars with site-controlled quantum dots (SCQDs) in the active layer. The SCQDs are grown via the buried stressor approach which allows for th…
A spiking photonic neural network of 40.000 neurons, trained with rank-order coding for leveraging sparsity
Ria Talukder, Anas Skalli, Xavier Porte +2
Spiking neural networks are neuromorphic systems that emulate certain aspects of biological neurons, offering potential advantages in energy efficiency and speed by for example lev…
Photonic neuromorphic computing using vertical cavity semiconductor lasers
Anas Skalli, Joshua Robertson, Dafydd Owen-Newns +5
Photonic realizations of neural network computing hardware are a promising approach to enable future scalability of neuromorphic computing. In this review we provide an overview on…
Coupled nonlinear delay systems as deep convolutional neural networks
Bogdan Penkovsky, Xavier Porte, Maxime Jacquot +2
Neural networks are currently transforming the field of computer algorithms, yet their emulation on current computing substrates is highly inefficient. Reservoir computing was succ…
Combining one and two photon polymerization for accelerated high performance (3+1)D photonic integration
Adria Grabulosa, Johnny Moughames, Xavier Porte +1
Dense and efficient circuits with component sizes approaching the physical limit is the hallmark of high performance integration. However, current fabrication technology is mostly…
Deterministic and stochastic coarsening control in optically-addressed spatial light modulators subject to optical feedback
Vladimir V. Semenov, Xavier Porte, Laurent Larger +1
Phase separation accompanied by further domain growth and coarsening is a phenomenon common to a broad variety of dynamical systems. In this connection, controlling such processes…
Chip-scale nanostructured chaotic billiards for broadband speckle spectrometry
Matthew R. Wilson, Benoit Guilhabert, Jack A. Smith +2
Computational on-chip spectrometers are emerging as a powerful platform for portable spectral analysis, combining photonic integration with advanced signal processing to enable a w…
Additive 3D photonic integration that is CMOS compatible
Adria Grabulosa, Johnny Moughames, Xavier Porte +2
Today, continued miniaturization in electronic integrated circuits (ICs) appears to have reached its fundamental limit. At the same time, energy consumption due by communication be…
Computational metrics and parameters of an injection-locked large area semiconductor laser for neural network computing
Anas Skalli, Xavier Porte, Nasibeh Haghighi +3
Artificial neural networks have become a staple computing technique in many fields. Yet, they present fundamental differences with classical computing hardware in the way they proc…
Convergence and scaling of Boolean-weight optimization for hardware reservoirs
Louis Andreoli, Stéphane Chrétien, Xavier Porte +1
Hardware implementation of neural network are an essential step to implement next generation efficient and powerful artificial intelligence solutions. Besides the realization of a…
Boolean learning under noise-perturbations in hardware neural networks
Louis Andreoli, Xavier Porte, Stéphane Chrétien +3
A high efficiency hardware integration of neural networks benefits from realizing nonlinearity, network connectivity and learning fully in a physical substrate. Multiple systems ha…
Direct (3+1)D laser writing of graded-index optical elements
Xavier Porte, Niyazi Ulas Dinc, Johnny Moughames +6
We propose single-step additive fabrication of graded-index optical elements by introducing the light exposure as the additional dimension to three-dimensional (3D) laser writing,…
Roadmap on Neuromorphic Photonics
Daniel Brunner, Bhavin J. Shastri, Mohammed A. Al Qadasi +147
This roadmap consolidates recent advances while exploring emerging applications, reflecting the remarkable diversity of hardware platforms, neuromorphic concepts, and implementatio…
Mutual coupling and synchronization of optically coupled quantum-dot micropillar lasers at ultra-low light levels
Sören Kreinberg, Xavier Porte, David Schicke +5
In this work we explore the limits of synchronization of mutually coupled oscillators at the crossroads of classical and quantum physics. In order to address this uncovered regime…
Quantum-optical spectroscopy of a two-level system using an electrically driven micropillar laser as resonant excitation source
Sören Kreinberg, Tomislav Grbešic, Max Strauà +6
Two-level emitters constitute main building blocks of photonic quantum systems and are model systems for the exploration of quantum optics in the solid state. Most interesting is t…
Reservoir-size dependent learning in analogue neural networks
Xavier Porte, Louis Andreoli, Maxime Jacquot +2
The implementation of artificial neural networks in hardware substrates is a major interdisciplinary enterprise. Well suited candidates for physical implementations must combine no…