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.

Subsidie
€ 1.672.528
2022

Projectdetails

Introduction

As artificial intelligence (AI) proliferates, hardware systems that can perform inference at ultralow latency, high precision, and low power are crucial and urgently required to deal especially quasi-locally, i.e., in the edge with massive and heterogeneous data. These systems must respond in real time, avoid unintended consequences, and function in complex and often unpredictable environments.

Limitations of Conventional Systems

Conventional digital electronics and the associated computer architecture are unable to meet these stringent requirements with sub-ms latency inference and a sub-10W power budget. This is particularly evident when using convolutional neural networks (CNNs) on benchmarks such as ImageNet classification.

HYBRAIN's Vision

HYBRAIN's vision is to realize a pathway for a radical new technology with ultrafast (~1 microsecond) and energy-efficient (~1 watt) edge AI inference. This will be based on a world-first, brain-inspired hybrid architecture of integrated photonics and unconventional electronics.

Brain-Inspired Architecture

The deeply entwined memory and processing, similar to that in the mammalian brain, obviates the need to shuttle around synaptic weights. The most stringent latency bottleneck in CNNs occurs in the initial convolution layers.

Innovative Approach

Our approach will take advantage of the ultrahigh throughput and low latency of photonic convolutional processors (PCPs) employing novel phase-change materials in these initial layers to radically speed up processing.

  1. Their output is processed using:
    • Cascaded electronic linear classifier layers
    • Nonlinear classifier layers based on memristive (phase-change memory) crossbar arrays
    • Dopant network processing units

Collaborative Efforts

HYBRAIN's science-towards-technology breakthrough brings together the world's top research groups from academia and industry in complementary technology platforms. Each of these platforms is already highly promising, but by integrating them, HYBRAIN will have a transformative effect on overcoming existing barriers of latency and energy consumption.

Future Applications

This integration will enable a whole new spectrum of edge AI applications throughout society.

Financiële details & Tijdlijn

Financiële details

Subsidiebedrag€ 1.672.528
Totale projectbegroting€ 1.672.528

Tijdlijn

Startdatum1-5-2022
Einddatum30-4-2026
Subsidiejaar2022

Partners & Locaties

Projectpartners

  • UNIVERSITEIT TWENTEpenvoerder
  • UNIVERSITAET MUENSTER
  • TRUST-IT SERVICES SRL
  • RUPRECHT-KARLS-UNIVERSITAET HEIDELBERG
  • IBM RESEARCH GMBH
  • THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD

Land(en)

NetherlandsGermanyItalySwitzerlandUnited Kingdom

Vergelijkbare projecten binnen EIC Pathfinder

EIC Pathfinder

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.

€ 2.455.823
EIC Pathfinder

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.

€ 1.973.038
EIC Pathfinder

Insect-Brain inspired Neuromorphic Nanophotonics

Developing nanophotonic chips inspired by insect brains for energy-efficient autonomous navigation and neuromorphic computing, integrating sensing and processing capabilities.

€ 3.229.534
EIC Pathfinder

n-ary spintronics-based edge computing co-processor for artificial intelligence

MultiSpin.AI aims to revolutionize edge computing by developing a neuromorphic AI co-processor that enhances energy efficiency and processing speed, enabling transformative applications while reducing CO2 emissions.

€ 3.143.276
EIC Pathfinder

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.

€ 2.982.184

Vergelijkbare projecten uit andere regelingen

ERC Starting...

Memristive self-organizing dendrite networks for brain-inspired computing

The MEMBRAIN project aims to develop self-organizing memristive nanonetworks for efficient, nature-inspired computing that mimics biological neural circuits, enhancing adaptability and intelligence.

€ 1.487.500
ERC Starting...

Memristive Neurons and Synapses for Neuromorphic Edge Computing

MEMRINESS aims to develop compact, power-efficient Spiking Neural Networks using memristive technology for enhanced collaborative learning on edge systems.

€ 1.499.488
ERC Consolid...

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.

€ 1.998.918
ERC Consolid...

Heterogeneous integration of imprecise memory devices to enable learning from a very small volume of noisy data

The DIVERSE project aims to develop energy-efficient cognitive computing inspired by insect nervous systems, utilizing low-endurance resistive memories for real-time decision-making in noisy environments.

€ 2.874.335
ERC Advanced...

ANalogue In-Memory computing with Advanced device TEchnology

The project aims to develop closed-loop in-memory computing (CL-IMC) technology to significantly reduce energy consumption in data processing while maintaining high computational efficiency.

€ 2.498.868