Machine Learning (ML) on the Edge for Speed and Security
Running Artificial Intelligence (AI) models on the edge involves processing data locally within embedded systems, which reduces latency and enhances privacy by minimizing data transmission to the cloud. This approach doesn’t require Internet connectivity and enables real-time decision making, making it a great solution for applications that require immediate responses and high reliability.
ML Inference Applications
Embedded Vision
Smart embedded vision technology enhances quality and productivity in factories, enables faster and more accurate medical diagnoses through machine assistance and provides granular, real-time monitoring and response for improved surveillance and security.
Human Machine Interface
Integrate local processing for voice interactive machines seamlessly with real-time, interactive gesture recognition to create a more responsive and intuitive smart HMI.
Sensor Analytics
Sensor systems can detect aging and environment-driven degradation, predict and prevent system failures and provide early warning for hazardous leaks to ensure optimal safety and efficiency.
Production-Ready Edge AI Solutions
These production-ready edge AI solutions are designed to move beyond prototypes and into real-world deployment. Each solution combines optimized silicon, embedded machine learning models and development tools to help teams bring intelligent systems to market faster and with greater confidence.
Arc Fault Detection
Smarter Protection, Faster Response
Detect dangerous electrical arc faults in real time using embedded machine learning. This solution delivers ultra-fast, standards-aligned detection with dramatically reduced false positives, improving safety, uptime and system reliability in high-energy environments.
Facial Recognition with Liveness Detection
Secure, On-Device Facial Recognition Intelligence
Bring robust facial recognition and liveness detection directly to the edge. Designed for real-world conditions, this solution enables secure, low-latency identity verification while keeping sensitive data on device and out of the cloud.
Keyword Spotting
Intelligent Voice at the Edge
Enable always-on, low-power voice control directly on embedded devices. This production-ready keyword spotting solution delivers fast, reliable command recognition without cloud dependency, enabling natural human-machine interaction in power- and cost-constrained systems.
Predictive Maintenance
Embedded Intelligence for Equipment Health
Transform raw sensor data into actionable maintenance insights at the edge. This predictive maintenance solution uses embedded machine learning to identify early signs of failure, helping reduce downtime, extend equipment life and lower operational costs.
Microchip Partners with Ceva to Enable AI Acceleration
“Collaborating with Ceva enables us to bring the full power of AI to our products, enabling richer, faster and more intelligent experiences for our customers.”
-Mark Reiten, Corporate Vice President of Microchip's Edge AI Business Unit
More Edge AI Solutions and Reference Designs
Coffee Type Detection Solution
Using AI to Detect Different Types of Coffee
We built a system with gas sensors and our PIC32CX microcontroller (MCU) that can classify three brands of coffee. This design can be used in food industry, industrial and healthcare applications.
Load Disaggregation Solution
Machine Learning-Based Load Disaggregation Solution
This demo showcases an efficient implementation of load disaggregation on an embedded microcontroller (MCU) to achieve the desired functionality with minimal CPU time and memory usage. This represents a key value-add for designers who are looking for optimal performance from our System-on-Chip (SoC) solutions for smart e-Metering applications.
Object Detection and Counting
Truck Loading Bay Monitoring Demo
The truck loading bay monitoring demo is an AI/ML demo based on a Faster Objects, More Objects (FOMO) object detection architecture.
Motion Surveillance
Rapidly Prototype With This Demo Application
Our motion surveillance demo application detects motion in front of an Arducam camera module using the motion-sensing PIR Click board™.
Gesture Recognition
Interpret and Respond to Human Gestures
This demo project outlines the process of data collection, transmission to the ML Model Builder, creation of a customized gesture recognition model for precise data classification and deployment onto the DSC using MPLAB ML Development Suite.
Sound Event Detection
Monitor Motor Sounds to Detect Anomalies
This tutorial will guide you through the process of building a vacuum cleaner sound recognizer with Edge Impulse and deploying it to the Microchip Curiosity Ultra development board.
PolarFire® FPGA Ethernet Sensor Bridge for the NVIDIA® Holoscan Software Development Kit (SDK)
The NVIDIA Holoscan platform provides hardware and software components to build streaming AI pipelines in edge and cloud AI applications such as industrial cameras, high-performance edge computers and medical devices. The hardware platform consists of a PolarFire FPGA Ethernet Sensor Bridge and NVIDIA Jetson™ AGX Orin™ and IGX Orin™ developer kit AI processing GPU platforms.
Deploy Your Models on Our Silicon Platforms
Whether you want to build your own model or bring your own, we have options to help you deploy your models on our MCUs, MPUs and FPGAs.
MPLAB® ML Development Suite
Build Your Own Model
Our MPLAB® ML Development Suite allows you to build efficient, low-footprint ML models for direct programming into our MCUs, MPUs and dsPIC® DSCs. Powered by AutoML, it streamlines model building and optimizes models for memory constraints with feature extraction, training, validation and testing. The API is fully convertible to Python for flexible model development.
MPLAB® Harmony v3
Bring Your Own Model
You can easily bring your existing Deep Neural Network (DNN) model to an MCU or MPU device. After converting a TensorFlow model to a LiteRT (formerly TensorFlow Lite) model, you can load the model to the device’s flash memory for inference. MPLAB® Harmony v3 can help you add the ML runtime engine and integrate it with other peripherals.
VectorBlox™ Accelerator SDK
Deploy Your Model on FPGAs
Use our state-of-the-art VectorBlox™ Accelerator Software Development Kit (SDK) to convert a high-level DNN to its lighter version (such as TensorFlow Lite) and deploy it on PolarFire® FPGAs.
Edge AI Design Partners
Our edge AI partner ecosystem extends our full-stack approach by bringing together leading technology and solution providers that accelerate real-world AI deployment. From edge analytics and sensor fusion to secure connectivity and cloud integration, these partners help customers move faster from development to production-ready edge AI systems.
221e
221e delivers sensor-fusion AI that combines multi-sensor data with embedded Machine Learning (ML) to enable real-time context awareness, anomaly detection and motion intelligence directly at the edge, without relying on the cloud.
Avnet /IOTCONNECTTM
Avnet’s /IOTCONNECT™ provides a secure edge-to-cloud platform for the creation, deployment and security of edge AI solutions at scale, enabling remote monitoring, analytics and lifecycle management of deployed devices.
Stream Analyze
Stream Analyze offers a lightweight analytics and AI platform that enables real-time data processing and ML inference on resource-constrained edge devices, supporting applications like predictive maintenance and condition monitoring.
Vedya Labs
Vedya Labs is an AI software and systems engineering partner that delivers optimized, production-ready edge AI solutions, helping semiconductor vendors and OEMs deploy real-time intelligence on embedded devices.
WGTech
WGTech Solutions provides end-to-end edge AI engineering services, including model development, optimization and deployment, helping customers move AI from prototype to production on embedded hardware.
Latest Edge AI Blogs
Addressing AI Server Power Density Requirements With Microchip’s MCPF1525 Power Module
Discover how the compact, high-current MCPF1525 power module’s advanced diagnostics, thermal management and programmable controls help design engineers build reliable, high-density AI servers.
The Importance of Retimers in Large Scale Generative AI Systems
Microchip META-DX2L PHY retimer enables scale-out for OCP-OAI 2.0.
Making Every Port Count: How Meta-DX2+ and XpandIO Bridge the Ethernet Speed Gap
Discover how our META-DX2+ with XpandIO bridges the Ethernet speed gap, enabling seamless aggregation and rate adaptation for legacy and high-speed networks.
Fortify Your Edge Computing Solutions: Fault Tolerance in Microprocessors
Discover how fault-tolerant microprocessors transform mission-critical edge computing from fragile to robust. Learn how our PIC64-HPSC and PIC64HX MPUs set new standards for reliability, resilience and security in the most demanding environments.