Silicon Labs
  • ⟵ Back
    Products
    2026 Tech Talks
    Get ready for deeper learning, bigger ideas, and the expert guidance to bring your next breakthrough to market faster.
    WirelessWireless
    Amazon Sidewalk
    Bluetooth
    LPWAN
    Matter
    Multiprotocol
    Proprietary
    Thread
    Wi-Fi
    Wi-SUN
    Z-Wave
    Zigbee
    Non-WirelessNon-Wireless
    MCUs
    Power Management
    Sensors
    USB Bridges
    IoT TechnologiesIoT Technologies
    Channel Sounding
    Energy Harvesting
    Machine Learning
    Security
    ServicesServices
    Custom Part Manufacturing
    Developer Services
    SDK Extended Maintenance Service
  • ⟵ Back
    Applications
    Smart HomeSmart Home
    Appliances
    Connected Outdoor
    Entertainment Devices
    IoT Gateways
    LED Lighting
    Security Cameras
    Sensors
    Smart Locks
    Switches
    Industrial IoTIndustrial IoT
    Access Control
    Asset Tracking
    Battery-Powered Tools
    Circuit Breakers
    Commercial Lighting
    Electric Submetering
    Emergency Lighting
    Factory Automation
    Human Machine Interface
    Industrial Wearables
    Predictive Maintenance
    Process Automation
    Smart HVAC
    Smart CitiesSmart Cities
    Battery Storage
    EV Charging Stations
    Smart Agriculture
    Smart Buildings
    Smart Metering
    Smart Solar PV System
    Street Lighting
    Smart RetailSmart Retail
    Commercial Lighting
    Direction Finding
    Electronic Shelf Labels
    Loss Prevention
    Wi-Fi Access Points
    Connected HealthConnected Health
    Portable Medical Devices
    Smart Hospitals
    Smart Wearable Devices
  • ⟵ Back
    Software & Tools
    Simplicity Studio 6
    Fast track IoT development
    Software & ToolsSoftware & Tools
    Simplicity AI SDK
    Software Development Kits (SDKs)
    SDK Release Notes
    Software Reference Documentation
    Software Development Tools
    Hardware Development Tools
    Hardware Documentation
    GitHub Resources
    Developer JourneysDeveloper Journeys
    AI/ML
    Amazon Sidewalk
    Bluetooth
    Bluetooth Mesh
    Google Home
    Matter
    Simplicity SDK for Zephyr
    Wi-Fi
    ServicesServices
    Custom Part Manufacturing
    Developer Services
    SDK Extended Maintenance Service
  • ⟵ Back
    Resources
    DocumentationDocumentation
    Blog
    Case Studies
    Software Documentation
    Technical Library
    Whitepapers
    TrainingTraining
    Tech Talks 2026
    Works With On-Demand 2025
    Webinars
    Curriculum
    PartnersPartners
    Channel & Distribution
    Ecosystem Partners
    Partner Network
    ServicesServices
    Custom Part Manufacturing
    Developer Services
    SDK Extended Maintenance Service
    SupportSupport
    Community
    Submit a Ticket
    Quality and Packaging
    How to Buy
    Report a Security Issue
    Contact Us
  • ⟵ Back
    Company
    About our CompanyAbout our Company
    Community Commitment
    Inclusion at Silicon Labs
    Management Team
    Security
    SustainabilitySustainability
    Environmental, Social & Governance
    Quality
    Supply Chain Responsibility
    News & EventsNews & Events
    Blog
    News Room
    Events
    Investor RelationsInvestor Relations
    Annual Report & Proxies
    Board of Directors
    Corporate Governance
    Quarterly Results
    SEC Filings
    CareersCareers
    Hyderabad Office
    Other Global Offices
    Contact Us
English
  • English
  • 简体中文
  • 日本語
Ask AI
AskAI
Ask AI
//
Applications // Machine Learning (ML) in IoT

IoT Machine Learning

Bringing Machine Learning to IoT applications reduces bandwidth requirements, saves power, and increases a device's ability to make smarter decisions. Silicon Labs supports machine learning in all its wireless SoCs, which enhances their acceleration speed using MVP (matrix vector processing) and consumes low power, thereby unlocking a plethora of new use cases.

Bringing Machine Learning to the IoT

Silicon Labs is redefining what's possible at the intersection of IoT and machine learning, enabling smarter, faster, and more efficient edge devices. Our platform brings together cutting-edge hardware and development tools to accelerate innovation in IoT machine learning applications, from smart homes to industrial automation. 

  • Integration with Wireless SoCs: Industry’s widest portfolio of wireless solutions combined with machine learning for IoT edge devices.
  • Deep Learning Neural Networks: Faster, more accurate, deep learning for advanced IoT machine learning applications
  • Rich Set of Development Tools: End-to-end ML in IoT toolchain designed for explorers and experts, speeding up development of smart connected products.
  • AI/ML Hardware Accelerator: Enables up to 8x faster inferencing at 1/6th the energy, reducing BOM and design complexity
  1. Hardware
  2. Software
  3. Development Tools
  4. Applications
  5. Partners
  1. Hardware

Getting Started With IoT Machine Learning Products

Our wireless SoCs feature a built-in Matrix Vector Processor (MVP) for hardware-accelerated IoT machine learning, enabling fast, low-power inferencing directly at the edge. Perfect for smart, connected devices requiring real-time, on-device intelligence.

EFR32MG24 Series 2 Multiprotocol Wireless SoC

The MG24 2.4 GHz wireless SoC is optimized for battery-powered IoT mesh devices in smart homes. A robust MVP accelerates inferencing and reduces power consumption.
More Information

EFR32MG24 Series 2 Multiprotocol Wireless SoC

The EFR32MG24 Wireless SoCs are ideal for mesh IoT wireless connectivity using Matter, OpenThread and Zigbee protocols for smart home, lighting, and building automation products. With key features like high performance 2.4 GHz RF, low current consumption, an AI/ML hardware accelerator and Secure Vault™, IoT device makers can create the smart, robust, and energy-efficient products that are secure from remote and local cyber-attacks. An ARM Cortex®-M33 running up to 78 MHz and up to 1.5 MB of Flash and 256 kB of RAM  provides resources for demanding applications while leaving room for future growth. Target applications include gateways and hubs, sensors, switches, door locks, LED lighting, luminaires, location services, predictive maintenance, glass break detection, wake-word detection, and more.

Visit EFR32MG24 Series 2 Multiprotocol Wireless SoC Family
X
Key Specs
Ideal applications
Smart Home, Lighting and Building Automation
Highest level of IoT Security
Secure Vault™

EFR32BG24 Series 2 Bluetooth Low Energy SoC - EFR32BG24

An SoC with high-performance wireless and low power for battery-efficient smart wearables. Has an integrated AI/ML accelerator and Secure Vault™ with the highest PSA Level 3 Certification.
More Information

EFR32BG24 Series 2 Bluetooth Low Energy SoC - EFR32BG24

The EFR32BG24 Wireless SoCs are ideal for IOT wireless connectivity using Bluetooth Low Energy and Bluetooth mesh for smart home, lighting, and portable medical products. With AECQ-100 qualification, support for Channel Sounding, and key features like high performance 2.4 GHz RF, low current consumption, an AI/ML hardware accelerator and Secure Vault™, IoT device makers can create the smart, robust, and energy-efficient products that are secure from remote and local cyber-attacks. An ARM Cortex®-M33 running up to 78 MHz and up to 1.5 MB of Flash and 256 kB of RAM provides resources for demanding applications while leaving room for future growth. Target applications include gateways/hubs, sensors, switches, door locks, smart plugs, LED lighting, luminaires, blood glucose meters and pulse oximeters.

Visit EFR32BG24 Series 2 Bluetooth LE SoC Family
X
Key Specs
Supports Bluetooth 6.0, Bluetooth mesh & Proprietary
Ideal for low-power battery-powered IoT devices

EFR32MG26 Series 2 Multiprotocol Wireless SoC

Future-proof multiprotocol SoC with a large Flash and RAM that is ideal for IoT mesh wireless connectivity in smart home, lighting, and building automation applications.
More Information

EFR32MG26 Series 2 Multiprotocol Wireless SoC

The EFR32MG26 Multiprotocol Wireless SoCs are the most future-proof wireless SoCs that are ideal for mesh IoT wireless connectivity using Matter, OpenThread, and Zigbee protocols for smart home, lighting, and building automation products. With key features like high-performance 2.4 GHz RF, low current consumption, an AI/ML hardware accelerator, and Secure Vault™, IoT device makers can create the smart, robust, and energy-efficient products that are secure from remote and local cyber-attacks. An ARM Cortex®-M33 running up to 78 MHz and up to 3 MB of flash and 512 kB of RAM enables more complex applications and provides headroom for Matter over Thread. Target applications include gateways and hubs, LED lighting, switches, sensors, locks, glass break detection, predictive maintenance, wake-word detection, and more.

Visit EFR32MG26 Series 2 Multiprotocol Wireless SoC Family
X
Key Specs
Large Flash and RAM
Up to 3 MB Flash and 512 kB RAM
Highest level of IoT Security
Secure Vault™

EFR32FG28 Sub-GHz Wireless + 2.4 GHz BLE SoCs

A dual band SoC for IoT smart home and metering applications that offers high design flexibility with high-performance Sub-GHz and BLE radios. An AI/ML MVP empowers implementation for Smart End Nodes.
More Information

EFR32FG28 Sub-GHz Wireless + 2.4 GHz BLE SoCs

The EFR32FG28 SoC is an ideal dual band Sub-GHz + 2.4 GHz Bluetooth LE SoC solution for IoT applications in smart homes, security, lighting, building automation, and metering. This dual band solution combines a high-performance Sub-GHz radio that provides long range capabilities and a Bluetooth radio for increased design flexibility. The large memory footprint and increased IO count allows for design consolidation and Secure Vault™ gives flexibility to choose the security level that meets your product’s needs.

Visit EFR32FG28 Sub-GHz Wireless + 2.4 GHz BLE SoCs Family
X
Key Specs
Up to 1024 kB of Flash and 256 kB of RAM
Sub-GHz and Bluetooth LE Support

SiWx917M Wi-Fi 6 plus Bluetooth LE 5.4 Wireless SoCs

A Wi-Fi 6 SoC optimized for ultra-low power IoT applications with Wi-Fi, Bluetooth, Matter, and AI/ML. A fully integrated design with an MVP extends battery life and enables secure cloud connectivity.
More Information

SiWx917M Wi-Fi 6 plus Bluetooth LE 5.4 Wireless SoCs

Our SiWx917M SoC is our lowest power Wi-Fi 6 SoC, ideal for ultra-low power IoT wireless devices using Wi-Fi®, Bluetooth, Matter, and IP networking for secure cloud connectivity. It is optimal for developing battery operated devices that need long battery life. SiWx917M SoC includes an ultra-low power Wi-Fi 6 and Bluetooth Low Energy LE 5.4 wireless CPU subsystem, and an integrated micro-controller (MCU) application subsystem, security, peripherals and power management subsystem all in a single 7x7 mm QFN package. The wireless subsystem consists of a Network Wireless Processor running up to 160 MHz, baseband digital signal processing, analog front end, 2.4 GHz RF transceiver and integrated power amplifier. The application subsystem consists of an ARM® Cortex®-M4F running up to 180 MHz, embedded SRAM, FLASH, and Sensor Hub. The ARM® Cortex®-M4F is dedicated for peripheral and application-related processing, while the network wireless processor runs the wireless and networking stacks on independent threads, thus providing a fully integrated solution that is ready for a wide range of embedded wireless IoT applications.

Target applications include Smart Homes, Consumer Health and Wearables, Medical, Industrial, Retail, Smart Building and Cities, Asset Tracking.

Visit SiWx917M Wi-Fi 6 plus Bluetooth LE 5.4 SoCs Family
X
Key Specs
Wi-Fi 6 and Bluetooth LE 5.4, Matter ready, ultra-low power, secure wireless radio
Integrated MCU, ARM® Cortex®-M4 processor with FPU
  1. Software

ML SDK: Simplify Machine Learning in IoT Development

The Silicon Labs ML SDK brings machine learning to IoT devices, seamlessly integrated into Simplicity Studio
and built upon the industry-standard TensorFlow Lite Micro framework.

How it Works:
 

Bring Your Own Model (BYOM): Start with your own TensorFlow Lite model or collaborate with our AI/ML partners to create a custom model tailored to your IoT use case.

Seamless Integration: Simply add the AI/ML SDK Extension when installing your Silicon Labs SDK, and drag and drop your model into the project's config folder to integrate it directly.

Automatic Optimization: From model conversion to deployment, the SDK manages optimization and hardware acceleration for you, making machine learning in IoT easier than ever.



Key Tools for IoT Machine Learning:

Flatbuffer Converter

Quickly convert .tflite models into deployable header files — just drop your model into your project’s config folder and you’re ready to go.

Flatbuffer Converter Tool

Model Profiler

Estimate memory usage and runtime performance on your IoT target device to fine-tune your model before deployment.

ML Model Profiler Sample Application

Model MVP Compiler

Integrated directly into Simplicity Studio, this compiler optimizes execution, managing memory layout, weight paging, and scheduling for efficient edge inferencing.

MVP Accelerator

Ready-to-go Demos 

Explore pre-built demos for voice, gesture, acoustic, and sensor-based recognition — showcasing the power of ML in IoT for real-world applications.

AI/ML Extension Sample Applications

Looking for more? Find more AI/ML software documentation here. Need help developing a model? Work with one of our partners  to create a custom model tailored to your use case.

  1. Development Tools

Getting Started With ML IoT Development Tools

Kickstart your IoT ML journey with our development kits and toolchain. Run out-of-the-box demos, evaluate model performance, and build custom IoT machine learning applications, all on hardware optimized for Edge AI. 

EFR32xG24 Dev Kit (xG24-DK2601B)

The EFR32xG24 Dev Kit is a compact, feature-packed development platform. It provides the fastest path to develop and prototype wireless IoT products. The development platform supports up to +10 dBm output power and includes support for the 20-bit ADC as well as other key features such as the xG24's AI/ML hardware accelerator.

Learn More

EFR32xG28 Explorer Kit (xG28-EK2705A)

The EFR32xG28 Explorer Kit is a small form factor development and evaluation platform based on the EFR32xG28 System-on-Chip. The kit is focused on rapid prototyping and concept creation of IoT applications for Sub-GHz and Bluetooth LE like Wi-SUN, Amazon Sidewalk, Z-Wave, Wireless M-Bus, and proprietary networks

Learn More

EFR32xG26 Explorer Kit (xG26-EK2709A)

The EFR32xG26 Explorer Kit, xG26-EK2709A, is small form factor development and evaluation platform based on the EFR32MG26 System-on-Chip focused on rapid prototyping and concept creation of IoT applications for 2.4 GHz wireless protocols including Bluetooth LE, Bluetooth mesh, Zigbee, Thread, and Matter.

Learn More
  1. Applications

Get Started with ML Application Examples

Explore how IoT machine learning enables real-time intelligence across a range of applications — from voice and audio detection to sensor signal processing and low-resolution vision. These use cases show how on-device AI unlocks smarter, faster, and more efficient edge solutions.

See each demo in action and learn how to build it using Silicon Labs hardware and development tools.

Sensor Signal Processing

Sensor signal processing is the use of low data rate sensors including accelerometers, gyroscopes, air quality sensors, temperature sensors, or pressure sensors. This makes it possible to extend machine life cycles, avoid down time, and reduce cost with preventive maintenance.

Audio Pattern Matching

Audio pattern matching uses microphones to detect a very wide range of non-speech related sounds including squeaky bearings, breaking glass, or running water. These features make it possible to bolster in-home security with glass break detector, scream, and shot detection.

Voice Commands

Voice commands are a specific sub-set of audio patterns that are the recognition of single words, which is also sometimes referred to as keyword spotting. Make a smart home a responsive home by turning lights on/off with AI/ML keyword detection.

Low-Resolution Vision

Make smart devices seeing devices by wake-up upon object detection, presence detection, people counting, and more.

  1. Partners

Get Started with our AI/ML IoT Partners

Accelerate your IoT machine learning development with trusted AI/ML partners. These pre-screened design service providers offer custom solutions or ready-to-deploy models on Silicon Labs SoCs, helping you simplify development and reduce time-to-market.

Edge Impulse Partner

Edge Impulse is the leading development platform for embedded machine learning, free for developers, and used by over 1,000 enterprises worldwide.

Learn More
SensiML Partner

SensiML pioneered software tools simplifying the development of TinyML code for IoT sensor applications.

Learn More
sensory Partner

Sensory Inc. creates a safer and superior UX through vision and voice technologies widely deployed in consumer electronics applications.

Learn More
Micro.ai Partner

MicroAI™ is an endpoint-based artificial intelligence and machine learning engine that lives directly on a device.

Learn More
ModelCat Partner

ModelCat is a team of experts with AI, IoT, systems design DNA, coming together to solve tough problems of advanced ML algorithms.

Learn More
Proud Member of the EdgeAI Foundation

Start your IoT Machine Learning development here.

Check out the AI/ML Developer Journey
AI/ML Developer Journey

IoT Machine Learning FAQs

Got questions about IoT machine learning? This section covers common topics like power use, deployment, and tools for building ML in IoT devices with Silicon Labs hardware.

Machine learning in IoT refers to running trained models directly on connected devices to process data from sensors, microphones, and cameras — enabling real-time decisions for use cases like voice recognition, vision processing, anomaly detection, and more, all without relying on the cloud.

Running machine learning models on IoT devices can reduce power consumption when using a hardware accelerator like Silicon Labs’ Matrix Vector Processor. For compute-heavy tasks such as matrix operations, the MVP can deliver up to 8x faster inference and up to 6x lower energy use compared to running the same model on the CPU, especially when dealing with larger workloads. This allows the CPU to remain idle or sleep, improving overall energy efficiency. 

No, you do not need internet access to run machine learning on IoT devices. With on-device inferencing and hardware acceleration, models can process data locally at the edge — enabling fast, reliable, and private IoT machine learning without relying on the cloud. 

You can get started in minutes using our ML development kits, which come with out-of-the-box demos — including a voice-controlled Pac-Man game. Check out our AI/ML Developer Journey for a step-by-step guide 

IoT with machine learning powers a wide range of applications including voice recognition, gesture detection, vision processing, predictive maintenance, anomaly detection, and smart access — all running efficiently on-device without cloud dependency.

Yes — you absolutely can. Our platform supports integration of pretrained models from popular frameworks, and our certified AI/ML partners offer ready-to-deploy solutions optimized for Silicon Labs hardware. Use them directly or finetune for your specific IoT machine learning application.

Silicon Labs offers a range of tools to help you evaluate and optimize machine learning in IoT devices. For example, the Model Profiler estimates memory usage and inference time on your target hardware, while the Model MVP Compiler (built into Simplicity Studio) optimizes model execution for efficient edge inferencing. These tools make it easy to fine-tune performance before deployment. 

No. Silicon Labs partners with trusted AI/ML providers who offer pre-built, ready-to-deploy solutions on our SoCs — ideal for teams looking to get started quickly. For custom applications, we also work with certified design service partners who can help you develop and deploy tailored IoT machine learning solutions without needing deep ML expertise.



IoT Machine Learning Demo Videos

Explore real-world IoT machine learning demos powered by our hardware accelerator. From voice and gesture recognition to fingerprint and acoustic sensing, these examples showcase fast, efficient on-device inferencing.

  • Now playing

    Voice Command Recognition with Pacman

    Voice Command Recognition with Pacman

  • Now playing

    Fingerprint Authentication Demo

    Fingerprint Authentication Demo

  • Now playing

    Guitar Note Recognition with AI/ML

    Guitar Note Recognition with AI/ML

  • Now playing

    ModelCat AI Demo

    ModelCat AI Demo

  • Now playing

    Rock, Paper, Scissors Gesture Recognition Demo

    Rock, Paper, Scissors Gesture Recognition Demo

Featured AI/ML Resources

Filter
Case Studies
Curriculum
Silicon Labs Blog
Tech Talk
AI/ML Developer Journey
AI/ML Developer Journey
Glass-Break Sensors Using Silicon Labs AI/ML-Enabled SoCs
Silicon Labs Blog
Glass-Break Sensors Using Silicon Labs AI/ML-Enabled SoCs
Unikie and Silicon Labs: Creating On-Device AI Solutions
Silicon Labs Blog
Unikie and Silicon Labs: Creating On-Device AI Solutions
Next-Gen IoT: Arduino and Silicon Labs Make Matter More Accessible with Edge AI and ML
Silicon Labs Blog
Next-Gen IoT: Arduino and Silicon Labs Make Matter More Accessible with Edge AI and ML
Silicon Labs and Eta Compute Simplify Edge-ML Development
Silicon Labs Blog
Silicon Labs and Eta Compute Simplify Edge-ML Development
MCU AI/ML - Bridging the Gap Between Intelligence and Embedded Systems
Silicon Labs Blog
MCU AI/ML - Bridging the Gap Between Intelligence and Embedded Systems
Silicon Labs Helps Waites Turn Sensor Data into Insight for AI-Powered Condition-Based Monitoring
Case Studies
Silicon Labs Helps Waites Turn Sensor Data into Insight for AI-Powered Condition-Based Monitoring
Tuya and Silicon Labs Accelerate Smart Lighting Innovation with No-Code Artificial Intelligence of Things Development Platform
Case Studies
Tuya and Silicon Labs Accelerate Smart Lighting Innovation with No-Code Artificial Intelligence of Things Development Platform
Emanate Wireless and Silicon Labs’ Machine Learning Open the Door to Affordable, Clinical-Grade RTLS for Hospitals of All Sizes
Case Studies
Emanate Wireless and Silicon Labs’ Machine Learning Open the Door to Affordable, Clinical-Grade RTLS for Hospitals of All Sizes
A Common MCU Platform for IoT Development
Tech Talk
A Common MCU Platform for IoT Development
AI/ML IoT Development Training: Works With 2022
Curriculum
AI/ML IoT Development Training: Works With 2022
AI/ML at the Edge – Works With 2023
Curriculum
AI/ML at the Edge – Works With 2023
Silicon Labs

Stay Connected With Us

Plug into the latest on Silicon Labs products, including product releases and resources, documentation updates, PCN notification, upcoming events, and more.

  • About Us
  • Careers
  • Community
  • Contact Us
  • Corporate Responsibility
  • Investor Relations
  • Press Room
  • Privacy and Terms
  • Site Feedback

Connect With Us:

Silicon Labs
Also of Interest:
  • MCU AI/ML - Bridging the Gap Between...
  • Artificial Intelligence & Machine Learning...
  • Silicon Labs SiWx917 Wi-Fi 6 Solution Features...
Copyright Silicon Laboratories. All rights reserved.

Your File Will Start Downloading Shortly

Thank you for downloading .

If you have any issues downloading, please contact sales support or product technical support.

Close
Loading Results
Close

Please select at least one column.