{"id":7990,"date":"2026-05-13T14:12:39","date_gmt":"2026-05-13T12:12:39","guid":{"rendered":"https:\/\/resmiq.org\/?page_id=7990"},"modified":"2026-05-13T15:56:33","modified_gmt":"2026-05-13T13:56:33","slug":"bridging-the-gap-between-deep-learning-and-edge-hardware","status":"publish","type":"page","link":"https:\/\/resmiq.org\/en\/bridging-the-gap-between-deep-learning-and-edge-hardware\/","title":{"rendered":"Bridging the Gap Between Deep Learning and Edge Hardware"},"content":{"rendered":"
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

For participants from outside Montreal (Universit\u00e9 Laval, Universit\u00e9 du Qu\u00e9bec en Outaouais, Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res, Universit\u00e9 de Sherbrooke, and Universit\u00e9 du Qu\u00e9bec \u00e0 Chicoutimi) contact Otmane Ait Mohamed (otmane.aitmohamed@concordia.ca<\/a>) for remote access.
<\/b><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Smail Niar
<\/strong>INSA Hauts-de-France and CNRS, France<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Date<\/strong> May 19, 2026
Hour :<\/strong> 11:00 AM \u2013 1:00 PM
Place<\/strong> Concordia University, EV Building, Room EV2.184, 1515 Ste-Catherine Street West, Montreal<\/p>

Summary:\u00a0 <\/strong>Deep learning (DL) models are being deployed to solve various computer vision and natural language processing tasks at the edge. Integrating DL on edge devices enables more efficient and responsive solutions. Hardware-aware Neural Architecture Search (HW-NAS)<\/em><\/strong> has recently gained steam by automating the design of efficient DL models for a variety of various target hardware platforms. In this talk I will present state-of-the-art approaches for HW-NAS that are based on three components:<\/p>

  1. Surrogate models to predict quickly architecture accuracy and hardware performances to speed up HW-NAS. The idea is to explore the prospect of Machine Learning for Machine Learning (ML4ML) by introducing techniques to estimate DL models performances on edge devices using neural architectural features and ML-based predictors.<\/li>
  2. Efficient multi-objective search algorithm that explores only promising hardware and software regions of the search space, and<\/li>
  3. New compression techniques that can be combined with HW-NAS to reduce the processing and memory complexities such as computational reuse and dynamic NAS.<\/li><\/ol>

    Biographical note:\u00a0<\/strong>Prof. Smail Niar<\/strong>, INSA Hauts-de-France\/Universit\u00e9 Polytechnique Hauts-de-France (UPHF) & CNRS, received his PhD in computer Engineering from the University of Lille (France) in 1990. Since then, he has been professor at UPHF and INSA Hauts-de-France. He is a member of the computer science department at the \u201cLaboratory of Automation, Mechanical and Computer Engineering\u201d, a joint research unit between CNRS and UPHF\/INSA. His research interests are AI\/ML-based embedded systems, autonomous transportation systems, HPC, and edge computing.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>","protected":false},"excerpt":{"rendered":"

    Pour les participants de l’ext\u00e9rieur de Montr\u00e9al (Universit\u00e9 Laval, Universit\u00e9 du Qu\u00e9bec en Outaouais, Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res, Universit\u00e9 de Sherbrooke, et Universit\u00e9 du Qu\u00e9bec \u00e0 Chicoutimi) contactez Otmane Ait Mohamed (otmane.aitmohamed@concordia.ca) pour l’acc\u00e8s \u00e0 distance. Smail NiarINSA Hauts-de-France and CNRS, France Date : 19 mai 2026Heure : 11h00 Read More\u2026<\/a><\/p>","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"axe-et-theme":[],"sujet":[],"class_list":["post-7990","page","type-page","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/pages\/7990","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/comments?post=7990"}],"version-history":[{"count":10,"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/pages\/7990\/revisions"}],"predecessor-version":[{"id":8012,"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/pages\/7990\/revisions\/8012"}],"wp:attachment":[{"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/media?parent=7990"}],"wp:term":[{"taxonomy":"axe-et-theme","embeddable":true,"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/axe-et-theme?post=7990"},{"taxonomy":"sujet","embeddable":true,"href":"https:\/\/resmiq.org\/en\/wp-json\/wp\/v2\/sujet?post=7990"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}