Machine learning

Hero section Title
SmartEdgeML: Run machine learning models on sensors
Hero section sub title
Ultra-low power execution of pre-trained machine learning (ML) algorithms directly on IMUs
About us section
Paragraph section title
Make smarter devices with on-sensor machine learning
Paragraph section description

TDK SmartEdgeML brings the power of machine learning  (ML) algorithms to motion sensors. Enable next-generation features such as activity and gesture recognition to smartwatches, hearable, wearables, and health monitors.

Image alignment
Right
Add paragraph image
Woman sitting on a couch listening to music with wireless over-ear headphones
key features grids
Key highlight grid title
Ultra-low power
key highlight short description

Run decision tree ML models on < 30 µA for always on sensing without sacrificing battery life

Image for key highlight
Simplified line icon depicting a fully charged battery
Key highlight grid title
Precise detection
key highlight short description

Easy activity and gesture detection through motion data machine learning

Image for key highlight
Simplified line icon depicting an arrow hitting the bullseye of a target
Key highlight grid title
Auto mode & easy development
key highlight short description

Developer tools to get started quickly, configure options, train, view performance metrics

Image for key highlight
Icons of a wrench and a screwdriver to represent the concept of tools
Key highlight grid title
Enable new use cases
key highlight short description

Train sensors to recognize human activities, motions, and gestures

Image for key highlight
Icon of an illuminated lightbulb
Key highlight grid title
Ensure data privacy
key highlight short description

Leverage highly personal user data without it ever leaving the sensor

Image for key highlight
Icon depicting a locked pad lock
Key highlight grid title
Improve battery life
key highlight short description

Machine learning can execute on sensors while the rest of the devices is asleep

Image for key highlight
Simplified line icon depicting a fully charged battery
Product spotlight section title
Machine Learning sensors
Product spotlight sub title
Explore popular sensors that can run ML models
Applications section paragraphs
Image alignment
Left
Hero primary button
Contact Us
Hero secondary button
Browse Products
Key features section title
TDK SmartEdgeML brings ML algorithms to sensors
Key features section sub title
Key capabilities of SmartEdgeML
Git hub resources section paragraphs
Image alignment
Left
Category grid section title
Add device ML intelligence to an array of applications
Category grid section sub title
SmartEdgeML enables personalized experiences for a range of devices
Category grids
Title
Smart glasses
Description
  • Run sensing algorithms on sensor for extra long battery life
  • Detect a variety of gestures and automated controls, including taps, donning and doffing, and voice detection 
Sub category grid sub title
Low power gesture, movement and direction awareness
Sub category grid icon
Close-up view of blue eye in glasses with futuristic holographic interface to display data
Title
Smartphones and PCs
Description
  • Detect in-car vs. walking
  • Program new device behaviors based on difficult to sense conditions 
Sub category grid sub title
Improve movement recognition as each device learns individual variations
Title
Wearables & hearables
Description
  • Reliably recognize and differentiate head, hand, and body gestures despite individual differences
  • Better differentiate between different activities and exercises 
Sub category grid sub title
Deliver accurate gesture and activity monitoring to enable new use cases
Sub category grid icon
Holographic display of health metrics above a tech-enabled wrist watch
Hero section background image
Abstract image of a laptop surrounded by interconnected data visualizations, light orbs, and infographic icons, depicting concepts of online security, global networking, data transfer, and digital communication, with a predominantly blue and purple color scheme
Machine learning