Join us at embedded world
April 9-11, 2024 at Nuremburg, Germany
Booth #4A-259
Join us at embedded world
April 9-11, 2024 at Nuremburg, Germany
Booth #4A-259
Learn
about Synaptics AstraTM, the AI-native compute platform for the IoT
Learn
about Synaptics AstraTM, the AI-native compute platform for the IoT
Explore
the newest edge AI compute and connectivity solutions
Explore
the newest edge AI compute and connectivity solutions
Discover
the latest techniques in edge AI model development and optimization
Discover
the latest techniques in edge AI model development and optimization
See
the most advanced automotive display technologies
See
the most advanced automotive display technologies
Learn
about Synaptics AstraTM, the AI-native compute platform for the IoT
Explore
the newest edge AI compute and connectivity solutions
Discover
the latest techniques in edge AI model development and optimization
See
the most advanced automotive display technologies
Enter embedded world for free
with Synaptics voucher code: ew24518199
Enter embedded world for free
with Synaptics voucher code: ew24518199
Astra Workshop
Register for a chance to be selected to work with AI-native compute solutions with the Synaptics Astra™ Developer Kit. Get a dev kit and software package. *Limited space available. Sign up today.
Live edge AI training
Register for a chance to be selected to work with AI-native compute solutions with the Synaptics Astra™ Developer Kit. Get a dev kit and software package. *Limited space available. Sign up today.
Date: Wednesday April 10, 2024
Start Time: 10:00 AM local Germany time
Where: Nuremberg Messe, NCC Mitte, Munchen 2
Duration: Three (3) hours
Date: Wednesday April 10, 2024
Start Time: 10:00 AM local Germany time
Where: Nuremberg Messe, NCC Mitte, Munchen 2
Duration: Three (3) hours
Synaptics Astra™: Accelerating the Transformation to an AI-Native IoT Edge
April 9, 2024 10:00 - 10:30am at Ausstellerforum Halle 5-210
Vikram Gupta
SVP & GM, IoT/Processors & Chief Product Officer
Synaptics Astra™: Accelerating the Transformation to an AI-Native IoT Edge
April 9, 2024 10:00 - 10:30am at Ausstellerforum Halle 5-210
Vikram Gupta
SVP & GM, IoT/Processors & Chief Product Officer
Expert Panel Session
Listen to the Synaptics experts talking about embedded vision and edge AI at NCC Ost.
Secure AI Inference for Embedded Vision Platforms
Abdel Younes
Director, Machine Learning Frameworks & Apps
April 9, 2024, 2:00pm-3:45pm
Embedded AI applications at the edge, including video analytics and enhancements, necessitate stringent data security measures to protect personal information and comply with legal and DRM requirements, despite often operating on encrypted video data. The session explores challenges in secure data processing and proposes solutions through secure inferencing frameworks, emphasizing efficient and protected handling of sensitive information in AI-driven video applications.
Hardware-Aware Joint Optimization of Model Architecture and Quantization
Karthik Vadivel
Principal Computer Vision Architect
April 9, 2024, 4:45pm-6:00pm
Neural network models for embedded applications are traditionally designed and optimized in two separate stages—architecture selection and quantization—which limits efficiency. We introduce a framework that unifies these stages using the Once-For-All approach, enhancing model performance and efficiency on target hardware by incorporating mixed-precision quantization and optimizing both architecture and quantization precision together, achieving faster and more memory-efficient models compared to conventional methods.
Object Detection in Images Using RNN
Dima Lvov
Senior Manager, Machine Learning
April 9, 2024, 12:00pm-12:30pm
To address the high resource demand of object detection on embedded devices, we replace CNN layers with RNN layers in object detection models, significantly reducing parameter count and power consumption. This novel approach, applied to a modified YOLOx5 model, maintains accuracy on the COCO dataset while offering lower latency, demonstrating RNN's efficiency over CNN for image-based inference.
Secure AI Inference for Embedded Vision Platforms
Abdel Younes
Director, Machine Learning Frameworks & Apps
April 9, 2024, 2:00-3:45pm
More info
Embedded AI applications at the edge, including video analytics and enhancements, necessitate stringent data security measures to protect personal information and comply with legal and DRM requirements, despite often operating on encrypted video data. The session explores challenges in secure data processing and proposes solutions through secure inferencing frameworks, emphasizing efficient and protected handling of sensitive information in AI-driven video applications.
Hardware-Aware Joint Optimization of Model Architecture and Quantization
Karthik Vadivel
Principal Computer Vision Architect
April 9, 2024, 4:45pm-6:00pm
More info
Neural network models for embedded applications are traditionally designed and optimized in two separate stages—architecture selection and quantization—which limits efficiency. We introduce a framework that unifies these stages using the Once-For-All approach, enhancing model performance and efficiency on target hardware by incorporating mixed-precision quantization and optimizing both architecture and quantization precision together, achieving faster and more memory-efficient models compared to conventional methods.
Object Detection in Images Using RNN
Dima Lvov
Senior Manager, Machine Learning
April 9th, 2024, 12:00pm-12:30pm
More info
To address the high resource demand of object detection on embedded devices, we replace CNN layers with RNN layers in object detection models, significantly reducing parameter count and power consumption. This novel approach, applied to a modified YOLOx5 model, maintains accuracy on the COCO dataset while offering lower latency, demonstrating RNN's efficiency over CNN for image-based inference.
Schedule a meeting
Complete the form below to schedule a meeting with our sales team at embedded world.