Edge AI Sensor Algorithms For the Smallest IoT Devices

Until now, generating real insight from IoT sensor nodes has required remote cloud processing, full stack edge gateways, or costly hand-coded custom algorithms optimized to fit inside embedded MCUs.

SensiML Toolkit is a breakthrough edge AI development tool that changes all that. Utilizing industry leading AutoML technology, SensiML empowers teams of all sizes and capabilities to be far more efficient in the development and commercialization of distributed intelligent sensing algorithms.

And SensiML's broad ML algorithm library generates code optimized for execution on devices ranging from multi-core x86 SBCs down to ARM M3 MCU-based IoT endpoints with only 10s of kBs to spare.


SensiML Analytics Toolkit Benefits At a Glance


If you can capture (or import) data representing what you seek to detect, SensiML's AutoML optimizer can automatically generate code for a predictive algorithm. Inordinate time and energy spent in iterative coding, testing, and re-coding can now be focused on improving your IoT application.


SensiML creates compact algorithms that execute locally on the embedded sensor node rather than the cloud or fat client edge gateways or PCs. Thus, your application benefits from distributed, fault-tolerant, real-time edge AI IoT processing right at the sensing endpoint.


With tools that address the entire workflow for AutoML algorithm design, SensiML Analytics Studio can streamline ALL aspects including initial prototyping and proof-of-concept work. Our tools allow developers to quickly test sensor applications on hardware in a matter of days or weeks rather than months.


Get your devices out of the lab and into the hands of customers sooner with ongoing edge AI learning that allow you expand model sophistication over time through crowd-sourced data feedback and regular updates. Your users can enjoy more engaging products as they contribute to solving their own corner case exceptions.

SensiML Analytics Toolkit suite automates each step of the process for creating optimized AI IoT sensor recognition code. The overall workflow uses a growing library of advanced ML and AI algorithms to generate code that can learn from new data either the development phase or once deployed.

Unlike many tools, SensiML has addressed the COMPLETE process providing tools to streamline collection and labeling of data on the front-end, optimization and hardware specific acceleration of core algorithms, and validation and testing of resulting code. Generated code is bit-exact between server emulation and corresponding embedded device code so developers can be confident what they see during code-gen will be what they get on device.

NXP Registered Partner Logo

SensiML Adds Support for NXP i.MX RT Crossover MCUs

Feb 26, 2020 - SensiML today announced support for NXP® Semiconductor’s i.MX RT portfolio of crossover microcontrollers via its SensiML Analytics Toolkit and plans to support out-of-the-box data collection with the NXP i.MX RT1050 evaluation kit.

More Info
ST Partner Program

SensiML Has Joined STMicroelectronics Partner Program to Deliver AI Solutions for IoT Endpoints

Dec 10, 2019 - SensiML Corporation, a leading developer of AI tools for building intelligent IoT endpoints, today announced that it has joined the STMicroelectronics Partner Program.

More Info
SensiML Logo

Free Software Toolkit Trial for AI-Based Wearable and Industrial IoT Applications"

Nov 25, 2019 - If you’re developing AI-based consumer wearable or industrial IoT products, you’ll likely be evaluating various software tools to help implement AI on your wearable or IoT device.

More Info