TECHNOLOGIES

Edge Impulse Demonstration of FOMO: Constrained Object Detection on Embedded Devices

Shawn Hymel, Senior Developer Relations Engineer at Edge Impulse, demonstrates the company’s latest edge AI and vision technologies and products at the 2023 Embedded Vision Summit. Specifically, Hymel demonstrates (“Faster Objects, More Objects”), a novel machine learning algorithm that brings object detection to highly constrained devices. FOMO lets you count objects, find the location of […]

Edge Impulse Demonstration of FOMO: Constrained Object Detection on Embedded Devices Read More +

Floating-point Arithmetic for AI Inference: Hit or Miss?

This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm. Our latest whitepaper shows that a new floating-point format doesn’t measure up to integer when you’re quantizing AI models to run on edge devices Artificial intelligence (AI) has become pervasive in our lives, improving our phones, cars,

Floating-point Arithmetic for AI Inference: Hit or Miss? Read More +

How are CMOS Cameras Used In Cell Imaging and Molecular Imaging?

This blog post was originally published at e-con Systems’ website. It is reprinted here with the permission of e-con Systems. CMOS cameras have revolutionized the fields of cell imaging and molecular imaging, providing accurate and detailed information about cellular and molecular processes. e-con Systems offers high-performance CMOS cameras designed for cell imaging and molecular imaging,

How are CMOS Cameras Used In Cell Imaging and Molecular Imaging? Read More +

Machine Learning 101: Build, Train, Test, Rinse and Repeat

This blog post was originally published at Tryolabs’ website. It is reprinted here with the permission of Tryolabs. In the previous episode of our Road to Data Science series, we went through all the general skills needed to become a proficient data scientist. In this post, we start to dig deeper into the specifics of

Machine Learning 101: Build, Train, Test, Rinse and Repeat Read More +

Edge Impulse Demonstration of Predictive Maintenance Using BrickML

Shawn Hymel, Senior Developer Relations Engineer at Edge Impulse, demonstrates the company’s latest edge AI and vision technologies and products at the 2023 Embedded Vision Summit. Specifically, Hymel demonstrates BrickML, a reference design for a tool that can monitor and measure machine health, using machine learning to detect anomalies and predicting when maintenance is needed.

Edge Impulse Demonstration of Predictive Maintenance Using BrickML Read More +

DEEPX Demonstration of Empowering Smart Camera and Robotics Applications with Edge AI Chip Technology

Tim Park, director of strategic marketing for DEEPX, demonstrates the company’s latest edge AI and vision technologies and products at the 2023 Embedded Vision Summit. Specifically, Park demonstrates how DEEPX’s edge AI chips enhance AI capabilities in existing product designs. In one of the demos, Park shows the simultaneous operation of multiple AI models. Explore

DEEPX Demonstration of Empowering Smart Camera and Robotics Applications with Edge AI Chip Technology Read More +

Intel Accelerates AI Development with Reference Kits

Optimized AI reference kits help developers and data scientists innovate faster. ​What’s New: Intel now offers a set of 34 open source AI reference kits to the community, the result of a yearslong collaboration with Accenture, enabling developers and data scientists to deploy artificial intelligence (AI) faster and more easily. Each kit includes model code, training data, instructions for

Intel Accelerates AI Development with Reference Kits Read More +

Supercharge Edge AI with NVIDIA TAO on Edge Impulse

We are excited to announce a significant leap forward for the edge AI ecosystem. NVIDIA’s TAO Toolkit is now fully integrated into Edge Impulse, enhancing our platform’s capabilities and creating new possibilities for developers, engineers, and businesses alike. Check out the Edge Impulse documentation for more information on how to get started with NVIDIA TAO

Supercharge Edge AI with NVIDIA TAO on Edge Impulse Read More +

Maximizing Attention, Minimizing Costs: Embracing Intelligent Digital Assistants with Vision and Speech Processing in the Cloud and Edge

This blog post was originally published by GMAC Intelligence. It is reprinted here with the permission of GMAC Intelligence. Humans mainly rely on speech, vision and touch to operate efficiently and effectively in the physical world. We also rely on smell and taste for our activities and our survival as well, but for most of

Maximizing Attention, Minimizing Costs: Embracing Intelligent Digital Assistants with Vision and Speech Processing in the Cloud and Edge Read More +

Transformer Models and NPU IP Co-optimized for the Edge

Transformers are taking the AI world by storm, as evidenced by super-intelligent chatbots and search queries, as well as image and art generators. These are also based on neural net technologies but programmed in a quite different way from more commonly understood convolution methods. Now transformers are starting to make their way to edge applications.

Transformer Models and NPU IP Co-optimized for the Edge Read More +

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top