{"id":9416,"date":"2022-10-05T16:23:50","date_gmt":"2022-10-05T14:23:50","guid":{"rendered":"https:\/\/www.l3s.de\/?page_id=9416"},"modified":"2026-06-03T10:20:49","modified_gmt":"2026-06-03T08:20:49","slug":"zuse-ki-mobil","status":"publish","type":"page","link":"https:\/\/www.l3s.de\/de\/research-at-l3s\/all-projects\/project-archive\/zuse-ki-mobil\/","title":{"rendered":"ZUSE-KI-mobil"},"content":{"rendered":"
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n\n\"\"\n
<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n

ZUSE-KI-mobil<\/h2>\n<\/div>\n<\/div>\n
\n
\n\nEnergieeffizienter Hardware-Beschleuniger f\u00fcr neuronale Netze in eingebetteten Anwendungen.<\/strong>\n\n<\/div>\n<\/div>\n
<\/div>\n
\n
\n
\n
\n
\n
\n
\n\nStart:\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n\n01.05.2020\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n
\n
\n\nEnde:\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n\n31.12.2025\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n
\n
\n\nWebseite:\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
elektronikforschung\/ki-mobil<\/a>\n<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n

ZUSE-KI-mobil<\/h2>\n<\/div>\n<\/div>\n
\n
\n\nEnergieeffizienter Hardware-Beschleuniger f\u00fcr neuronale Netze in eingebetteten Anwendungen.<\/strong>\n\n<\/div>\n<\/div>\n
<\/div>\n
\n
\n\nZiel des Projekts ist die Entwicklung eines KI-Beschleunigers mit einer flexiblen, erweiterbaren und skalierbaren System-on-Chip-Architektur (SoC). Der Beschleuniger ist auf einen geringen Energieverbrauch f\u00fcr KI-Algorithmen im autonomen Fahren optimiert und wird in der energieeffizienten 22-nm-FDX-Halbleitertechnologie gefertigt. Dar\u00fcber hinaus etabliert Zuse-KI-mobil ein \u00d6kosystem, das ein Entwicklungssystem und ein deutsches Partnernetzwerk mit Expertise im KI-Hardwaredesign kombiniert. Schlie\u00dflich wird die Flexibilit\u00e4t und Skalierbarkeit der Prozessorplattform anhand von Demonstratoren verifiziert.<\/span>\n\n<\/div>\n<\/div>\n
<\/div>\n
\n
\n\nF\u00f6rderprogramm<\/a>\n
<\/span><\/div>\n
<\/span><\/div>\n
\n
\n
\n
\n\n\u2013\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n\nProjektpartner<\/a>\n
<\/span><\/div>\n
<\/span><\/div>\n
\n
\n
\n
\n\n\u2013<\/span>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n
\n
\n

Kontakt<\/h1>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n
\n\n\"\"\n
<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n

Prof. Dr.-Ing. Holger Blume<\/h4>\n<\/div>\n<\/div>\n
\n
\n\nProjektmanager\n\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n
\n
<\/span> blume@l3s.de<\/a>\n<\/span><\/div>\n<\/div>\n
\n
<\/span> +49 511 762-19640<\/a>\n<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"

ZUSE-KI-mobil Energy-efficient hardware accelerator for neural networks in embedded application. Start: 01.05.2020 End: 31.12.2025 Website: elektronikforschung\/ki-mobil ZUSE-KI-mobil Energy-efficient hardware accelerator for neural networks in embedded application. The project aims to develop an AI accelerator with a flexible, expandable, and scalable system-on-chip (SoC) architecture. For low energy consumption, the accelerator is optimized for AI algorithms in […]<\/p>\n","protected":false},"author":7,"featured_media":9414,"parent":10129,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"page-templates\/full-width-page.php","meta":{"_acf_changed":false,"footnotes":""},"categories":[75],"tags":[119],"class_list":["post-9416","page","type-page","status-publish","has-post-thumbnail","hentry","category-project-archive","tag-archive"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t