{"id":4183,"date":"2025-08-26T12:56:59","date_gmt":"2025-08-26T10:56:59","guid":{"rendered":"https:\/\/silicon-austria-labs.com\/?p=4183"},"modified":"2026-07-30T09:31:20","modified_gmt":"2026-07-30T07:31:20","slug":"international-success-austrian-research-partnership-sets-new-standards-in-neuromorphic-computing","status":"publish","type":"post","link":"https:\/\/silicon-austria-labs.com\/en\/internationale-erfolge-oesterreichische-forschungs-partnerschaft-setzt-neue-massstaebe-im-neuromorphic-computing\/","title":{"rendered":"Inter\u00adna\u00adtional Success: Austrian Re\u00adsearch Part\u00adner\u00adship Sets New Stan\u00addards in Neuro\u00admor\u00adphic Computing"},"content":{"rendered":"

Neuro\u00admor\u00adphic Computing is an emerging tech\u00adnology designed to make arti\u00adfi\u00adcial intel\u00adli\u00adgence (AI) faster and more energy-effi\u00adcient. For the past three years, the Insti\u00adtute for Signal Process\u00ading at Johannes Kepler Univer\u00adsity Linz (JKU), Silicon Austria Labs (SAL), and the Soft\u00adware Compe\u00adtence Center Hagen\u00adberg (SCCH) have been working closely together, pooling their exper\u00adtise to advance this exciting field.<\/strong><\/p>\n

Neuro\u00admor\u00adphic Computing \u2013 Inspired by the Brain<\/h2>\n

Unlike clas\u00adsical computers, which process infor\u00adma\u00adtion in bits, the human brain uses short elec\u00adtrical impulses\u2014known as spikes. What matters is the precise timing of these spikes, which carries the actual infor\u00adma\u00adtion.<\/p>\n

This timing-based repre\u00adsen\u00adta\u00adtion allows the brain to transmit more complex infor\u00adma\u00adtion per signal compared to a digital bit, which can only be \u201c0\u201d or \u201c1.\u201d The inter\u00advals between spikes and their patterns carry addi\u00adtional meaning, making this highly effi\u00adcient for tasks such as detecting patterns or sequences in real time. In tech\u00adnology, these prin\u00adci\u00adples are repli\u00adcated by so-called Spiking Neural Networks (SNNs).<\/p>\n

\u201cOur goal is to develop systems that mimic biolog\u00adical struc\u00adtures and processes\u2014using minimal energy while achieving maximum respon\u00adsive\u00adness,\u201d explains Priv.-Doz. Dr. Bern\u00adhard A. Moser, Tech\u00adnology and Inno\u00adva\u00adtion Manager at SCCH. \u201cPoten\u00adtial appli\u00adca\u00adtions include robotics, medical tech\u00adnology, and envi\u00adron\u00admental moni\u00adtoring.\u201d<\/p>\n

Dispelling Common Myths<\/h2>\n

Despite growing interest, several miscon\u00adcep\u00adtions about Neuro\u00admor\u00adphic Computing (NC) persist\u2014such as the assump\u00adtion that it requires expen\u00adsive, special\u00adized hard\u00adware, is slower than tradi\u00adtional methods, or lacks indus\u00adtrial matu\u00adrity.\n\u201cWe show that many of these assump\u00adtions are outdated,\u201d says Dr. Thomas Buchegger, Head of the SAL site in Linz. \u201cNC offers tremen\u00addous poten\u00adtial not only in energy effi\u00adciency but also in speed. More\u00adover, it can be effec\u00adtively imple\u00admented on stan\u00addard hard\u00adware plat\u00adforms\u2014not just special\u00adized analog chips.\u201d<\/p>\n

A recent joint study by JKU, SAL, SCCH, and TU Graz has demon\u00adstrated NC\u2019s versa\u00adtility in the medical field. Researchers found a way to collect and process elec\u00adtro\u00adcar\u00addio\u00adgram (ECG) data far more effi\u00adciently\u2014reducing data volume by more than 80% without sacri\u00adficing analysis quality. This means lower storage require\u00adments while main\u00adtaining the same accu\u00adracy, opening up signif\u00adi\u00adcant oppor\u00adtu\u00adni\u00adties for the future of medical diag\u00adnos\u00adtics and beyond.<\/p>\n

Milestones of the Research Partnership<\/h2>\n

Since the beginning of their collaboration, the partners have achieved a number of pioneering successes that impressively underscore the international potential of neuromorphic computing \u201eMade in Austria\u201c:<\/p>\n

World Record for SNN Inference on Standard FPGAs<\/h2>\n

Using a newly devel\u00adoped demon\u00adstrator, the team has shown that Spiking Neural Networks can run at excep\u00adtional speeds on widely avail\u00adable FPGA (Field Program\u00admable Gate Array) systems.<\/p>\n

\u201cOur method processes over 2.5 million images per second\u2014more than 100 times faster than previous systems using the same hard\u00adware and data,\u201d says Assoc. Prof. Dr. Michael Lunglmayr from JKU\u2019s Insti\u00adtute for Signal Process\u00ading. \u201cIt also oper\u00adates at low power, achieving more than 3 million images per second per watt.\u201d<\/p>\n

This break\u00adthrough illus\u00adtrates how modern AI can be both highly powerful and energy-effi\u00adcient\u2014on off-the-shelf hard\u00adware.<\/p>\n

Patent Filed<\/h2>\n

The team has filed a patent for a novel, ultra-energy-effi\u00adcient data acqui\u00adsi\u00adtion method based on neuro\u00admor\u00adphic prin\u00adci\u00adples inspired by the human brain.<\/p>\n

Austrian Workshop Series and Publications<\/h2>\n

Through the SNNSys work\u00adshop series on Neuro\u00admor\u00adphic Computing and Spiking Neural Networks, orga\u00adnized in collab\u00ado\u00adra\u00adtion with TU Graz as part of the AIROV confer\u00adence, the part\u00adners are driving knowl\u00adedge exchange within Austria\u2019s re\u00adsearch commu\u00adnity. Find\u00adings have been published in leading jour\u00adnals such as the Journal of Neuro\u00admor\u00adphic Computing and Engi\u00adneering and presented at top-tier confer\u00adences, including the IEEE Inter\u00adna\u00adtional Sympo\u00adsium on Circuits and Systems.<\/p>\n

Inter\u00adna\u00adtional Grand Chal\u00adlenge<\/h2>\n

In September 2025, at the pres\u00adti\u00adgious IEEE Inter\u00adna\u00adtional Confer\u00adence on Image Process\u00ading (ICIP) in Alaska, the re\u00adsearch team will host an inter\u00adna\u00adtional chal\u00adlenge under its motto \u201cLow Energy, High Speed.\u201d The compe\u00adti\u00adtion aims to iden\u00adtify the most effi\u00adcient and fastest AI solu\u00adtions.<\/p>\n

\u201cWe\u2019re excited to see the creative and inno\u00adv\u00ada\u00adtive approaches this will inspire,\u201d says Moser. \u201cThe strong interest from the scien\u00adtific commu\u00adnity shows the incred\u00adible momentum in this field.\u201d<\/p>\n

About the research partners<\/h2>\n

Software Competence Center Hagenberg (SCCH)<\/a><\/h3>\n

Soft\u00adware Compe\u00adtence Center Hagen\u00adberg (SCCH) is a leading non-univer\u00adsity re\u00adsearch center in Austria, special\u00adizing for over 20 years in applied re\u00adsearch in the fields of Data Science and Soft\u00adware Science. SCCH excels in project imple\u00admen\u00adta\u00adtion for digi\u00adtal\u00adiza\u00adtion, Industry 4.0, and Arti\u00adfi\u00adcial Intel\u00adli\u00adgence, serving as an inter\u00adface between inter\u00adna\u00adtional re\u00adsearch and domestic industry. The center employs around 130 staff from 25 nations, conducting world-class re\u00adsearch. As a COMET Center (Compe\u00adtence Centers for Excel\u00adlent Tech\u00adnolo\u00adgies), SCCH is funded by the Austrian Federal Ministry for Trans\u00adport, Inno\u00adva\u00adtion and Tech\u00adnology, the Federal Ministry for Digi\u00adtal\u00adiza\u00adtion and Busi\u00adness Loca\u00adtion, and the State of Upper Austria.<\/p>\n

Press contacts:<\/strong><\/p>\n

    \n
  • Mag. Martina H\u00f6ller, Science Communication, Software Competence Center Hagenberg, (+43) 50 343 882, martina.hoeller@scch.at<\/li>\n
  • Priv.-Doz. Dr. Bernhard A. Moser, Technology and Innovation Manager at SCCH and co-initiator of this cooperation, also works with a double affiliation at the Institute for Signal Processing at Johannes Kepler University Linz (JKU). bernhard.moser@scch.at<\/li>\n<\/ul>\n

    Johannes Kepler Univer\u00adsity Linz (JKU) \u2013 Insti\u00adtute for Signal Process\u00ading (ISP)<\/h3>\n

    The Insti\u00adtute for Signal Process\u00ading (ISP) at Johannes Kepler Univer\u00adsity Linz is a leading acad\u00ademic re\u00adsearch unit special\u00adizing in the algo\u00adrithmic, archi\u00adtec\u00adtural, and hard\u00adware-oriented aspects of signal process\u00ading systems. Its re\u00adsearch spans infor\u00adma\u00adtion and commu\u00adni\u00adca\u00adtion systems, high-frequency and base\u00adband inte\u00adgrated circuits (ICs), bio- and sensor signal process\u00ading, and auto\u00admo\u00adtive appli\u00adca\u00adtions.<\/p>\n

    For nearly 60 years, the Johannes Kepler Univer\u00adsity has been rooted in regional tradi\u00adtion but endowed with a strong inter\u00adna\u00adtional perspec\u00adtive. As Upper Austria\u2019s largest insti\u00adtu\u00adtion of educa\u00adtion and re\u00adsearch, the univer\u00adsity offers degree programs and conducts re\u00adsearch in the fields of law, engi\u00adneering, natural sciences, medi\u00adcine, educa\u00adtion, social sciences, economics and busi\u00adness. The JKU campus is home to approx\u00adi\u00admately 25,000 enrolled students and close to 4,000 employees, boasting a modern infra\u00adstruc\u00adture with ample space to study, learn, conduct re\u00adsearch, and enjoy univer\u00adsity life.<\/p>\n

    Press contacts:<\/strong><\/p>\n

      \n
    • Mag. Christian Savoy, University Communications, +43 732 2468 3012, christian.savoy@jku.at<\/li>\n
    • Associate Professor Dr. Michael Lunglmayr, co-initiator of the cooperation,<\/li>\n
    • Michael.lungl\u00admayr@jku.at<\/li>\n<\/ul>\n

      Silicon Austria Labs (SAL)<\/h3>\n

      Silicon Austria Labs (SAL) is Austria's top re\u00adsearch center for elec\u00adtronics and soft\u00adware-based systems (ESBS), which are the tech\u00adno\u00adlog\u00adical back\u00adbone of digi\u00adti\u00adza\u00adtion. At three loca\u00adtions in Graz, Villach and Linz, SAL conducts cutting-edge re\u00adsearch in Microsys\u00adtems, Sensor Systems, Power Elec\u00adtronics, Intel\u00adli\u00adgent Wire\u00adless Systems, and Embedded Systems to develop future-oriented solu\u00adtions for indus\u00adtrial produc\u00adtion, health, energy, mobility, and safety.<\/p>\n

      The Intel\u00adli\u00adgent Wire\u00adless Systems divi\u00adsion focuses on devel\u00adoping reli\u00adable and secure commu\u00adni\u00adca\u00adtion systems for indus\u00adtrial envi\u00adron\u00adments. This enables broad\u00adband connec\u00adtions for mobile devices (e.g., smart\u00adphones, tablets, laptops), wire\u00adless machine-to-machine commu\u00adni\u00adca\u00adtion, and increas\u00adingly wire\u00adless sensor networks in indus\u00adtrial appli\u00adca\u00adtions.<\/p>\n

      One of SAL\u2019s flag\u00adship initia\u00adtives is Digineuron, a pioneering project aimed at devel\u00adoping ultra-effi\u00adcient inte\u00adgrated circuits that imple\u00adment AI in minia\u00adture formats. These chips mimic the struc\u00adture and func\u00adtion of the human brain, using layered neural networks that commu\u00adni\u00adcate locally to mini\u00admize energy consump\u00adtion \u2014 opening new possi\u00adbil\u00adi\u00adties for smart, low-power appli\u00adca\u00adtions.<\/p>\n

      SAL brings together key players from industry, science, and re\u00adsearch, combining valu\u00adable exper\u00adtise and know-how to conduct coop\u00ader\u00ada\u00adtive, appli\u00adca\u00adtion-oriented re\u00adsearch along the value chain. Coop\u00ader\u00ada\u00adtive projects are co-financed by SAL and enable a fast and unbu\u00adreau\u00adcratic project start.<\/p>\n

      Press contacts:<\/strong><\/p>\n

        \n
      • DI Dr. Thomas Buchegger, thomas.buchegger@silicon-austria.com<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"

        Neuro\u00admor\u00adphic Compu\u00adting ist eine neue Tech\u00adno\u00adlogie, um K\u00fcnst\u00adliche Intel\u00adli\u00adgenz (KI) zu verbes\u00adsern. Das Ziel ist es, KI ener\u00adgie\u00adspa\u00adrender und schneller zu machen. Seit drei Jahren arbeiten das Institut f\u00fcr Signal\u00adver\u00adar\u00adbei\u00adtung der Johannes Kepler Uni-versit\u00e4t Linz (JKU), die Silicon Austria Labs (SAL) und das Soft\u00adware Compe\u00adtence Center Hagen\u00adberg (SCCH) eng zusammen und b\u00fcndeln ihre Fach\u00adkennt\u00adnisse, um […]<\/p>\n","protected":false},"author":5,"featured_media":4184,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-4183","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"acf":{"isevent":false,"location":"","eventdate":null,"eventtime":null},"_links":{"self":[{"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/posts\/4183","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/comments?post=4183"}],"version-history":[{"count":7,"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/posts\/4183\/revisions"}],"predecessor-version":[{"id":4484,"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/posts\/4183\/revisions\/4484"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/media\/4184"}],"wp:attachment":[{"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/media?parent=4183"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/categories?post=4183"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/silicon-austria-labs.com\/en\/wp-json\/wp\/v2\/tags?post=4183"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}