Abstract:
Deploying increasingly large and complex deep learning networks onto resource-constrained devices is a growing challenge facing many AI practitioners, especially within the domain of audio and acoustic applications. Modern deep neural networks, which are integral to advancing state-of-the-art signal processing algorithms, typically require high-performance processors and/or GPUs due to their extensive number of learnable parameters. As these large AI models set new benchmarks for quality and functionality, they simultaneously push the boundaries of what can be embedded into real-time systems and edge devices. Consequently, engineers today are faced with the critical task of reconciling the complexity of these networks with the stringent resource limitations of portable devices and low-power sensors, while ensuring real-time performance without compromising accuracy.
In this talk, attendees will explore a realistic industrial workflow, that integrates an AI model, trained to detect component faults in an air compressor, into a system before deploying to an edge device. The talk will include:
• A discussion on why an AI solution is appropriate.
• Selecting a suitable model and network architecture.
• Integrating and validating the AI model in a larger system design using Simulink.
• Automatically generating target optimized C/C++ implementations and deploying to an edge device.
Please register to attend at the following link: https://recruitment.mathworks.com/flows/cambridge-university-computer-labs-tech-talk-2025-vecm0c4c4
Some catering will be provided
