Edge Impulse (Hall 4, Booth 505) will highlight collaborations with leading silicon partners, including STMicroelectronics, at embedded world 2025 with its in-booth demonstrations such as the STM32N6, ST’s new flagship microcontroller, which delivers a 600x performance gain over current high-end STM32 microcontrollers thanks to the integration of the Neural-ART Accelerator, an advanced NPU from STMicroelectronics.

Austin, Texas. Ambiq is joining the Edge Impulse network to deliver scalable AI models on the Apollo4 Plus System-on-Chip (SoC) ideal for edge AI such as speech, health, and more AI applications. The Apollo4 Plus utilizes Subthreshold Power Optimization Technology (SPOT) to achieve 10X more proficiency for AI processing vs. other Arm M4-based solutions.

 

Join Edge Impulse at Embedded World North America to witness how it is transforming edge AI projects by empowering developers and ML engineers to build datasets (including with synthetic data), train models, and optimize libraries to run directly on device, from the smallest microcontrollers to gateways, with the latest neural accelerators (and everything in between).

San Jose, California. Edge Impulse announced an innovation enabling visual anomaly detection on any edge device, from NVIDIA GPUs to Arm MCUs, through the first model architecture of its kind, FOMO-AD (Faster Objects, More Objects - Anomaly Detection). To enhance the productivity of visual inspection systems, the scalable FOMO-AD can train models to identify and index anything outside set criteria as an anomaly in video and image data.

San Jose, California. The Edge Impulse Studio platform now has native support for Particle's new Photon 2 board. The team-up of Edge Impulse and Particle powers edge AI with the integration of the Particle ecosystem into deployment of trained AI models to the Photon 2 board.  The collaboration is the first IoT Integration for Edge Impulse.

BrickML is a standalone device for measuring and monitoring machine health with machine learning (ML). It tracks current (MCSA), vibration, temperature, and audio via its integrated sensors and onboard computer. Using advanced ML algorithms, BrickML analyzes data on the device itself to detect subtle changes in machine behavior, predicting potential failures before they occur. The compact design allows for easy integration into existing systems, providing real-time data analysis and actionable insights, right at the edge. It is fully integrated into the Edge Impulse platform, allowing users to quickly and easily create AI algorithms for their specific use cases. 

Syntiant Corp unveiled its TinyML Development Board, a developer kit aimed at both technical and non-technical users building machine learning-powered applications in smart products, such as speech commands, wake word detection, acoustic event detection, and other sensor use cases.