Companies including NVIDIA, Arm, Capgemini and Nestlé Purina will present at the conference as industrial edge AI moves from R&D into production-scale deployments

SAN JOSE, Calif.: Edge Impulse, the leading platform for building, deploying, and scaling edge machine learning models, has unveiled a suite of new industry first edge AI tools designed for industrial environments at its fourth annual Imagine conference.

Users on Edge Impulse’s Enterprise plan can apply for early access to the new suite of tools and models designed for industrial applications, including:

YOLO-Pro: Cutting-edge object detection for the production line. YOLO-Pro, based on the popular YOLO (You Only Look Once) algorithm, is the first model of its kind trained with extensive industrial datasets for optimal performance in real-world edge scenarios. Built from the ground up to outperform existing YOLO architectures, YOLO-Pro is also licensable for all businesses and optimized and available in various sizes to run efficiently on edge devices from CPUs to accelerators to GPUs.

Application Behavior: Tune models for real-world industrial performance. Build end-to-end applications that optimize models in the full context of a deployment against desired business outcomes. This solution empowers customers to optimize the entire machine learning application simultaneously, ensuring peak performance on edge AI devices. Supported applications include sound and speech detection, object tracking and counting, fall detection and many more.

Model Monitoring: Deploy in production confidently on fleets of devices. Continuously monitor and improve edge AI models at scale for optimal performance and rapid issue resolution:

• Deploy, analyze, and debug models on device with your IoT solution of choice
• Enrich and refine your models with data from the field
• Deliver seamless over-the-air (OTA) updates
• Monitor in-production model metrics

AI Actions: GenAI Tooling for Industrial Use Cases. Accelerate machine learning development and enhance model performance by building high-quality datasets faster. Leverage large language models (LLMs) to create automated data pipelines for efficient data labeling and automated quality control. Harness the power of generative AI and NVIDIA Omniverse to create and enhance sensor, audio, and vision datasets with synthetic data. Integrate with established GenAI platforms including OpenAI, HuggingFace, ElevenLabs, and custom LLM sources.

“Edge AI has matured significantly in the past year, particularly in industrial, logistics and transportation where companies are eager to optimize productivity and safety,” said Zach Shelby, co-founder and CEO at Edge Impulse. “Edge Impulse's new offerings are customized to professional needs and were built based on what we've learned from our active deployments with customers. We are making it easy to advance edge AI models from prototype to production with enterprise-grade reliability, security, and monitoring capabilities.”

"Edge Impulse is leading the way in establishing best practices for the successful deployment of edge AI use cases in practical, real-world environments," said Carolyn Swan, Director Partnerships at Advantech. "Industrial IoT is maturing quickly and Edge Impulse deployed on Advantech’s Edge AI-enabled hardware is providing essential professional tools to advance AI capabilities for this market."

The company also published a report with Manufacturing Dive’s studioID today that surveyed 150 manufacturing leaders, and 133 Edge Impulse users, to share insights into the growing adoption of edge AI for industrial use cases and the need for more advanced tooling.

“Leveraging production-grade customized AI models presents a challenging task that requires numerous iterations and fine-tuned optimizations, including extensive field trials, said Saeid Safavi, Ph.D., co-founder and CEO at Global Sense Inc. "Edge Impulse helps us achieve these goals more swiftly and effectively by streamlining the entire development cycle—from data preparation and sanitization to the deployment of the AI model on-device.”

Learn more about Edge Impulse’s new suite of industrial edge AI tools at the company’s Imagine 2024 conference on September 24 online or at the Computer History Museum in Mountain View, California along with executives from Capgemini, Nestlé Purina, NVIDIA, and other business leaders. Sign up for the early access program here.

About Edge Impulse

Edge Impulse streamlines the creation of AI and machine learning models for edge hardware, allowing devices to make decisions and offer insight where data is gathered. Edge Impulse’s technology empowers developers to bring more AI products to market, and helps enterprise teams rapidly develop production-ready solutions in weeks instead of years. Powerful automations make it easier to build valuable datasets and develop advanced AI for edge devices from MCUs to CPUs to GPUs. Used by health and wearable organizations like Hyfe and Ultrahuman, industrial organizations like Lexmark, HP, and Halma as well as top silicon vendors and over 100,000 developers, Edge Impulse has become the trusted ML platform for enterprises and developers alike. To learn more, visit edgeimpulse.com.

Fonte: Business Wire