Digital optical computing platform for neural networks
DOLORES aims to develop a digital optical neural network processor to overcome current optical computing limitations, revolutionizing AI and deep learning applications across various sectors.
Projectdetails
Introduction
Artificial Intelligence - humanity’s new frontier - has dramatically progressed during the past decade due to the introduction of deep learning. Deep learning applications usually require vast amounts of computing resources but microelectronics are encountering physically fundamental bottlenecks in speed, energy consumption, heating, and interconnect delay, which can no longer be resolved by scaling.
Challenges in Microelectronics
The end of Moore’s law urgently calls for the introduction of new devices, new integration technologies, and new architectures to efficiently accelerate deep learning applications. Recently, optical neural networks (ONNs) based on photonic integrated circuits have shown great potential as an emerging computing architecture beyond von Neumann and Moore to overcome the bottlenecks in their microelectronics counterparts.
Obstacles in ONNs
Yet the ONN concepts and demonstrations so far are encountering severe obstacles such as:
- Limited calculation precision
- Repeatability
- Scalability
- Compatibility with microelectronics
These obstacles are deeply rooted in the analogue computing architecture of the existing ONNs: insufficient signal-to-noise ratio due to accumulated noise and crosstalk in the system.
Project Overview
DOLORES aims to explore and develop a radically new digital optical computing platform to create a new class of processors, namely a digital optical neural network (DONN) processor, that is fundamentally different from any ONN scheme and solves the aforementioned obstacles.
Vision and Impact
Integrating the best of photonics and electronics, DOLORES is expected to revolutionize optical computing, and in the long-term vision enable new possibilities that are barely supported by today’s computing hardware. If successful, DOLORES can pave the way for a new era in AI, drastically accelerating neural networks and deep learning applications, which have the potential to transform many sectors of our society, including healthcare, finance, and transportation.
Financiële details & Tijdlijn
Financiële details
Subsidiebedrag | € 3.015.883 |
Totale projectbegroting | € 3.015.883 |
Tijdlijn
Startdatum | 1-9-2024 |
Einddatum | 31-8-2028 |
Subsidiejaar | 2024 |
Partners & Locaties
Projectpartners
- DANMARKS TEKNISKE UNIVERSITETpenvoerder
- TECHNISCHE UNIVERSITEIT EINDHOVEN
- INTERUNIVERSITAIR MICRO-ELECTRONICA CENTRUM
- NEDERLANDSE ORGANISATIE VOOR TOEGEPAST NATUURWETENSCHAPPELIJK ONDERZOEK TNO
- KOBENHAVNS UNIVERSITET
- UNIVERSITY OF SOUTHAMPTON
Land(en)
Vergelijkbare projecten binnen EIC Pathfinder
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
RECONFIGURABLE SUPERCONDUTING AND PHOTONIC TECHNOLOGIES OF THE FUTURERESPITE aims to develop a compact, scalable neuromorphic computing platform integrating vision and cognition on a single chip using superconducting technologies for ultra-low power and high performance. | EIC Pathfinder | € 2.455.823 | 2023 | Details |
Neuromorphic computing Enabled by Heavily doped semiconductor OpticsNEHO aims to create a novel photonic integrated circuit for ultrafast, low-energy neuromorphic processing using nonlinear photon-plasmon technology to enhance machine learning capabilities. | EIC Pathfinder | € 2.982.184 | 2023 | Details |
Hybrid electronic-photonic architectures for brain-inspired computingHYBRAIN aims to develop a brain-inspired hybrid architecture combining integrated photonics and unconventional electronics for ultrafast, energy-efficient edge AI inference. | EIC Pathfinder | € 1.672.528 | 2022 | Details |
Nano electro-optomechanical programmable integrated circuitsNEUROPIC aims to develop a programmable photonic chip architecture for diverse applications, leveraging nanoelectromechanical technologies to enhance efficiency and enable neuromorphic computing. | EIC Pathfinder | € 2.999.924 | 2023 | Details |
SPIKING PHOTONIC-ELECTRONIC IC FOR QUICK AND EFFICIENT PROCESSINGSPIKEPro aims to develop an integrated neuromorphic chip combining electrical and photonic neurons to create efficient, high-speed spiking neural networks for diverse applications. | EIC Pathfinder | € 1.973.038 | 2024 | Details |
RECONFIGURABLE SUPERCONDUTING AND PHOTONIC TECHNOLOGIES OF THE FUTURE
RESPITE aims to develop a compact, scalable neuromorphic computing platform integrating vision and cognition on a single chip using superconducting technologies for ultra-low power and high performance.
Neuromorphic computing Enabled by Heavily doped semiconductor Optics
NEHO aims to create a novel photonic integrated circuit for ultrafast, low-energy neuromorphic processing using nonlinear photon-plasmon technology to enhance machine learning capabilities.
Hybrid electronic-photonic architectures for brain-inspired computing
HYBRAIN aims to develop a brain-inspired hybrid architecture combining integrated photonics and unconventional electronics for ultrafast, energy-efficient edge AI inference.
Nano electro-optomechanical programmable integrated circuits
NEUROPIC aims to develop a programmable photonic chip architecture for diverse applications, leveraging nanoelectromechanical technologies to enhance efficiency and enable neuromorphic computing.
SPIKING PHOTONIC-ELECTRONIC IC FOR QUICK AND EFFICIENT PROCESSING
SPIKEPro aims to develop an integrated neuromorphic chip combining electrical and photonic neurons to create efficient, high-speed spiking neural networks for diverse applications.
Vergelijkbare projecten uit andere regelingen
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Three dimensional INtegrated PhotonIcS to RevolutionizE deep LearningThis project aims to develop advanced photonic neural network processors to significantly enhance computational efficiency and scalability, revolutionizing AI hardware and applications. | ERC Consolid... | € 1.998.918 | 2022 | Details |
Large-scale Multicore Smart Photonics: Using advanced design and configuration protocols to develop the largest-scale programmable photonic processorThe project aims to develop a large-scale multicore programmable photonic processor to enhance scalability and performance in integrated photonics for complex neuromorphic computing applications. | ERC Starting... | € 1.499.325 | 2023 | Details |
measuriNg nEURal dynamics with label-free OpticaL multI-DomAin RecordingsThis project aims to innovate label-free optical methods for monitoring neural dynamics in the brain, enhancing understanding and treatment of brain diseases without exogenous reporters. | ERC Starting... | € 1.634.825 | 2025 | Details |
3D integrated photonic nanostructures with Giant optical nonlinearity3DnanoGiant aims to develop innovative nonlinear photonic materials using liquid crystals for efficient all-optical signal processing in integrated photonic devices. | ERC Starting... | € 1.500.000 | 2025 | Details |
Optical polarization for ultrafast computingLOOP aims to create an ultrafast optical Ising machine using light polarization to solve NP-hard optimization problems in microseconds, surpassing current digital and analog hardware speeds. | ERC Starting... | € 1.499.928 | 2025 | Details |
Three dimensional INtegrated PhotonIcS to RevolutionizE deep Learning
This project aims to develop advanced photonic neural network processors to significantly enhance computational efficiency and scalability, revolutionizing AI hardware and applications.
Large-scale Multicore Smart Photonics: Using advanced design and configuration protocols to develop the largest-scale programmable photonic processor
The project aims to develop a large-scale multicore programmable photonic processor to enhance scalability and performance in integrated photonics for complex neuromorphic computing applications.
measuriNg nEURal dynamics with label-free OpticaL multI-DomAin Recordings
This project aims to innovate label-free optical methods for monitoring neural dynamics in the brain, enhancing understanding and treatment of brain diseases without exogenous reporters.
3D integrated photonic nanostructures with Giant optical nonlinearity
3DnanoGiant aims to develop innovative nonlinear photonic materials using liquid crystals for efficient all-optical signal processing in integrated photonic devices.
Optical polarization for ultrafast computing
LOOP aims to create an ultrafast optical Ising machine using light polarization to solve NP-hard optimization problems in microseconds, surpassing current digital and analog hardware speeds.