H2020Индивидуална стипендия2017–2019

PHOTON-NeuroCom · Photonic-assisted Neuromorphic Computing system

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2017-08-01 → 2019-07-31
Финансиране от ЕС: 212 195 €
Участници: 1
Схема: MSCA-IF-EF-ST

Линиите свързват координатора с партньорите.

Накратко на български

Фотонните невроморфни системи изследват компютърни архитектури, вдъхновени от работата на човешкия мозък, вместо от стандартните процесори. Те ще помогнат за по-бърза обработка на данни и спестяване на енергия при устройства като дронове, смарт камери и медицинска техника.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Photonic-assisted Neuromorphic Computing system

Conventional computing systems (like CPUs in PCs, Smartphones and etc.) will inevitably within the next 10 years reach a limit because of fundamental scientific reasons including limits on manufacturing, speed, density, transistor technology , power constraints . The most promising solution to this are the brain-inspired computing systems, so-called neuromorphic computing system (NCS). Implementation of NCSs using conventional transistor technology (CMOS) is area- and power-inefficient. Such inefficiencies have driven a significant effort to investigate the development of beyond-CMOS NCSs. The non-CMOS implementation of synapse has been researched to be implemented by spin-based materials (memristors, MTJs, STNOs and etc.). Despite some progress, still there is a huge difference (5-6 orders of magnitude) between the performance (operation/sec/Watt/cm3) of state-of-the-art NCS and human brain. Neuromorphic computing market is expected to reach USD 1.7 billion by 2025 with an annual growth of 86%. Such growth shows the importance of neuromorphic computing and it is expected to find a huge market with the exponential growth of data processing, especially images and videos. In this respect, the social impact of PHOTON-NeuroCom’s technology can be tremendous. PHOTON-NeuroCom’s technology would allow for on-device computation, saving energy, speed, and improving privacy. PHOTON-NeuroCom will bring huge impact on society and EU economy, and the possibilities of new market creation is overwhelming, e.g. medical devices, edge devices, drones, space applications, military, IoT, smart vehicles, surveillance, smart cameras, financial forecasting, data mining, life-long self-learning machines etc. The overall aim of PHOTON-NeuroCom was to realize a novel integration platform that combines photonic with current combination of the spin-based material and electronic (i.e. spintronic) in order to achieve an energy-efficient and high-speed brain-inspired computing system. The overall objectives of PHOTON-NeuroCom can be listed as: 1-Modelling the effect of heating on the dynamic and static behaviors of MTJ/STNO and the interaction between laser and MTJ/STNO 2-Design and simulation of a real-time laser-assisted MTJ/STNO-based NCS 3-Validating the models and designed systems by experimental results

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

Neuromorphic computing has emerged as a promising approach to mimic the brain by overcoming the limitation of the conventional computers. The current implementation of neuromorphic computing systems (NCSs) has been done in CMOS technology, which comes with area and power-inefficiency. Enormous effort has been devoted to optimize the area and power-efficiency of such NCSs. One of the most promising approaches is the implementation of NCSs using spin-based devices combined with electronics (i.e. spintronics). Although, power-density is improved by spintronics-based NCSs, they are still far from the power-density of the brain that is attributed to the traditional way of changing the state of magnetic moment using a bias current that contributes to 90% of the total power consumed by such NCSs. Given a technique eliminating or decreasing this bias current, the power density of NCSs can be improved by orders of magnitude. PHOTON-NeuroCom proposes a novel approach that adds the benefits from photonics to the current spintronics-based NCSs by replacing the large bias current of the state of the art NCSs with a short polarized laser pulse. This will lead to at least two and three orders of magnitude lower energy consumption and higher speed in comparison with the state-of-the-art spintronics-based NCSs. This is a major step towards filling the huge gap between the power density of human brains and computers. The main objectives of this project are to model magnetic-photonic interaction, design and simulate a NCS through extracted model and fabrication of photonic-assisted STNO.My previous experience with spintronics and mixed signal IC design has put me in a unique position to run such a promising project. On the other hand, I will benefit from a supervision team from host and partner organization with more than 15 years of experience in photonic integrated circuits and IC design. Moreover, the running FET-OPEN project at Aarhus University will speed up my fellowship.

Оригинален текст от CORDIS (на английски).

Участници

AARHUS UNIVERSITET · Aarhus CКоординаторДания