DE · Topics · Resources · Design · Sponsored Content

Using Synthetic Datasets to Train Embedded AI

This study demonstrates training and validating embedded AI algorithms using synthetic datasets derived from large numbers of parametric cloud simulations.

Using synthetic datasets to train AI is a fast, cost effective way to deploy robust embedded algorithms for new hardware technologies. Synthetic datasets generated from cloud simulations can be created in hours using the OnScale platform, compared to weeks or months to create similar datasets from physical experimentation.

This whitepaper discusses how an embedded AI algorithm for 3D smartphone touchscreens was trained and validated using the results of 8,000 simulations run in parallel on AWS. The demonstrated approach of using synthetic datasets to train AI networks can drastically reduce cost, risk, and time for the development of new hardware technologies.

OnScale is fully cloud-enabled, empowering engineers with the high-performance computing (HPC) resources needed to explore their design space quickly and with ease. Semiconductors, MEMS, sensors, medical devices, and 5G and IoT RF systems are among the many applications that can benefit from design and optimization with OnScale. To learn more visit onscale.com/applications.

Contents

  • Problem: 3D touch technology operation
  • Introduction: Using Synthetic Datasets to Train Embedded AI
  • Approach: Simulating a synthetic data set & AI training
  • Results: AI Performance

Fill out the information below to download the resource.

By downloading this content, I agree to receive the DE 24/7 Newswire, a twice weekly free email newsletter (you may choose to opt-out in the newsletter).

Latest News

Weber State Installs Impossible Objects CBAM 3D Printer
The Composite-Based Additive Manufacturing (CBAM) system is installed at Weber State University's MARS Center at Hill Air Force Base, UT.

What’s New in Simcenter Mechanical Simulation
Simcenter Mechanical tools let users model the complexity of products.

Asking the Right Questions About HPC for Simulation
The answers to those questions may shed light on what services are most needed.

Matterport to Provide Digital Twin Platform for John Deere Operations
John Deere will use Matterport’s digital twin platform to streamline facilities and operations management to boost responsivity and productivity,...

All posts