BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:MathWorks: Embedded AI: Deploying deep learning models for industr
 ial applications  - Antoni Woss\, Ruth Faherty and Iason Chaimalas
DTSTART:20250203T130500Z
DTEND:20250203T135500Z
UID:TALK223024@talks.cam.ac.uk
CONTACT:Ben Karniely
DESCRIPTION:Abstract:  \nDeploying increasingly large and complex deep lea
 rning networks onto resource-constrained devices is a growing challenge fa
 cing many AI practitioners\, especially within the domain of audio and aco
 ustic applications. Modern deep neural networks\, which are integral to ad
 vancing state-of-the-art signal processing algorithms\, typically require 
 high-performance processors and/or GPUs due to their extensive number of l
 earnable parameters. As these large AI models set new benchmarks for quali
 ty and functionality\, they simultaneously push the boundaries of what can
  be embedded into real-time systems and edge devices. Consequently\, engin
 eers today are faced with the critical task of reconciling the complexity 
 of these networks with the stringent resource limitations of portable devi
 ces and low-power sensors\, while ensuring real-time performance without c
 ompromising accuracy. \nIn this talk\, attendees will explore a realistic 
 industrial workflow\, that integrates an AI model\, trained to detect comp
 onent faults in an air compressor\, into a system before deploying to an e
 dge device. The talk will include:\n\n•	A discussion on why an AI soluti
 on is appropriate.\n\n•	Selecting a suitable model and network architect
 ure.\n \n•	Integrating and validating the AI model in a larger system de
 sign using Simulink.\n\n•	Automatically generating target optimized C/C+
 + implementations and deploying to an edge device. \n\nPlease register to 
 attend at the following link: https://recruitment.mathworks.com/flows/camb
 ridge-university-computer-labs-tech-talk-2025-vecm0c4c4 \n\nSome catering 
 will be provided
LOCATION:FW26\, William Gates Building
END:VEVENT
END:VCALENDAR