In most software domains, developers don’t write code at the bare-metal level; they build applications on top of operating systems, which provide commonly needed functionality. Yet, today, developers of video and AI applications are effectively writing their applications at the […]
In the fast-paced world of embedded vision applications, moving rapidly from concept to deployment is crucial. In this presentation, Dan Mihai Dumitriu introduces the Edge App Runtime and SDK—groundbreaking tools designed to streamline and accelerate the development process for edge […]
In this session, we’ll outline the key steps required to implement a large language model (LLM) on a Raspberry Pi. We’ll begin by outlining the motivations for running LLMs on the edge and exploring practical use cases for LLMs at […]
As artificial intelligence inference transitions from cloud environments to edge locations, computer vision applications achieve heightened responsiveness, reliability and privacy. This migration, however, introduces the challenge of operating within the stringent confines of resource constraints typical at the edge, including […]
Running AI algorithms on battery-powered, low-cost devices requires a different approach to designing hardware and software. The power requirements are stringent at standby, but the device needs to be able to awaken quickly when an event is detected. The device […]
In the rapidly evolving landscape of intelligent transportation systems (ITSs), the demand for efficient and reliable solutions has never been greater. In this presentation, we show how an innovative approach—optimized vision language models—can dramatically enhance the accuracy and robustness of […]
Machine vision is the most obvious way to help humans live better, enabling hundreds of applications spanning security, monitoring, inspection and more. Modern edge processors need private on-device and scalable hybrid machine learning capabilities to offer enough longevity to stay […]
In this presentation, we will explore the challenges of accuracy and performance when implementing quantized machine learning inference algorithms on embedded systems. We’ll explain how the thoughtful use of fixed-point data types yields significant performance and efficiency gains without compromising […]
Transformers are a class of neural network models originally designed for natural language processing. Transformers are also powerful for visual perception due to their ability to model long-range dependencies and process multimodal data. Resource constraints form a central challenge when […]
At a time when IC fabrication costs are skyrocketing and applications have increased in complexity, it is important to minimize design risks and maximize flexibility. In this session, learn how embedding FPGA technology can solve these problems—expanding your market access […]
Want to contact us?
Use the small blue chat widget in the lower right-hand corner of your screen, or the form linked below.
STAY CONNECTED
Follow us on Twitter and LinkedIn.
