Edge Impulse is an embedded machine learning platform that allows you to manage Machine Learning Ops (MLOps) for the edge, include data acquisition, signal processing, ML training, model testing, and create a deployable model that can run efficiently on an edge device.

Ease of Use

• Easy to scale, no need to learn multiple tools for your edge AI pipeline
• Powerful automation

Test and fine-tune the performance of your models with real-world data to identify issues before deploying to your device.

Optimize for any edge hardware in a single click with our hardware export selection tool.

Deploy trained models as an optimized C++ library to any edge device.

Build Smarter Products, Faster

EON Tuner: Make Better Decisions

The EON Tuner is an engineering tool designed to empower developers to select the best processing and model parameters given their device constraints for their specific application. Typically, this task can only be achieved by domain experts using complex model training systems and codebases.

EON Compiler: Reduce Model Size Without Sacrifice.

Build neural networks with up to 55% Less RAM and 35% Less ROM! Dramatically reduce RAM and ROM usage in ML models without sacrificing accuracy or increasing latency.

FOMO (Faster Objects More Objects): Automation For Objects

FOMO is a ground-breaking algorithm that brings real-time object detection, tracking and counting to microcontrollers for the first time. Count objects, find the location of objects in an image, and track multiple objects in real-time.

Get to Market Faster

AI is a key initiative discussed at every level of organizations that want to be relevant three years from now. Edge Impulse supercharges the ability to scale the development of ML/AI models for edge targets and applications, ensuring innovative teams can achieve more than ever before with purpose-built cutting edge resources

Edge Impulse is a software platform that enables organizations to build, deploy, and scale edge AI faster and more seamlessly than ever.

Products or services of Edge Impulse

Edge Impulse is a software platform that simplifies the development of ML models for the edge, where data is collected, with or without connectivity. We have pioneered a way to get insights to previously unattainable locations, on or off the cloud. You can now reduce cost, accelerate time to market, improve outcomes, and derisk product deployment.

Enjoy the freedom to work with any data, any sensor, any processor, any code and deliver large models, tuned and compressed, to run efficiently on any edge device and royalty free; you made it, you own it.

Edge Impulse in STMicroelectronics ecosystem

Build. Train. Optimize. AI for the edge.

Build datasets, train models, and optimize libraries to run on any edge hardware. Edge Impulse empowers ML teams to run AI at peak performance on any edge device, with unmatched ease and speed.

Unlock sensor data value

• Advance algorithm development
• Optimize edge AI models
• Target agnostic edge deployment

Easily integrate with existing ML workflows

• Collaborate across your data, ML, and embedded teams to build optimized production-ready models faster.
• Achieve measurable results Future-proof your products
• Our customers win by adding edge intelligence to their products, from low-power wearables to industrial gateways.

We play fair:

• Royalty-free business model — no impact on BOM cost
• Your IP stays your IP
• Total explainability, no black boxes

Edge Impulse: Related Resources

(#STM32MPU) (#STM32MP1) (#STM32U595) (#STM32H7S) (#STM32AIServicesCertifiedPartner)