Beyond 2020 - Vision SoCs for the Edge

Ready to take your next smart SoC to the next level? In this video series, you’ll find the latest info on bringing visual intelligence into the embedded systems you use every day, in cars, mobile devices, wearables and cameras. Industry leaders and Synopsys innovators are here to share their expertise. Whether your AI interest is in deep neural networks at the extreme edge, sensor fusion for autonomous vehicles, early and accurate power estimation, or car safety with security, you’ll find something to help you get your innovative SoC to market fast.

Enabling DNNs at the Extreme Edge: Co-optimization Across Circuits, Architectures, and Algorithmic Scheduling

Marian Verhelst, Associate Professor at KU Leuven and Scientific Director at imec

Deep neural network inference comes with significant computational complexity, making their execution often feasible only on power-hungry server or GPU platforms. The recent trend towards embedded neural network processing on edge and extreme edge devices requires thorough cross layer optimization. Learn how to optimize NPU/TPU processor architectures, dataflow schedulers and quantized neural network models for to optimize latency and energy efficiency.

Sensor Fusion for Autonomous Vehicles: Strategies, Methods, and Tradeoffs

Robert Laganière, Professor, School of Electrical Engineering and Computer Science, University of Ottawa

Understand the advantages and disadvantages of the different sensors used in intelligent vehicles. Learn the main sensor fusion strategies that can be used for combining heterogeneous sensor data and the three main fusion methods that can be applied in a perception system: early fusion, late fusion and mid-level fusion.

Trends for Embedded Vision & AI in Edge Applications

Pierre Paulin, R&D Director, Synopsys

Embedding computer vision and deep learning at the edge remains challenging because of 1) huge computational and memory requirements, and 2) the accelerating pace of innovation for algorithms that perform modern vision and sensing tasks. Learn about the latest trends in machine learning for edge applications, including emerging models like EfficientNet and new techniques like Transformers. Understand key challenges and opportunities with a specific focus on bandwidth optimization.

Estimating Power Early & Accurately for Smart Vision SoCs

Derya Eker, R&D Manager, Synopsys

Today’s high-end SoCs need to handle increasingly compute-intensive workloads but must carefully balance power-to-performance tradeoffs. To optimize for power and performance, hardware becomes more tightly intertwined with software. Learn the key architectural choices that designers must consider throughout the development process, such as hardware/software workload partitioning and when to estimate power tradeoffs for the most accurate results.

Safe & Secure SoC Architectures for Autonomous Vehicles

Fergus Casey, R&D Director, Synopsys

Learn about the challenges that SoC designers and OEMs face when developing self-driving vehicles, from understanding how a pedestrian looks to software/silicon, to understanding an entire scene. Learn the key milestones that the industry, and each chip design, must reach on the road to autonomous driving, and how to know when you've reached them.

Ready to learn more?