Blog Posts

The Next Frontier in AI Is Not Just Reasoning. It Is Knowing When to Look Again

Why AI Metacognition Requires Hierarchical Random-access Data   This blog post was originally published at V-Nova’s website. It is reprinted here with the permission of V-Nova. Executive Summary (TL;DR) Today’s AI systems can reason impressively, but they still struggle to know when to look again. Humans use metacognition as a feedback loop between thought and perception: […]

The Next Frontier in AI Is Not Just Reasoning. It Is Knowing When to Look Again Read More +

ChiPy: Bridge Neural Networks and C++ on Silicon — Full Inference Pipelines with Zero CPU Round-Trips

This blog post was originally published at Quadric’s website. It is reprinted here with the permission of Quadric. The ChiPy DSL is Quadric’s Python framework for building complete on-chip pipelines. Using YOLOX-M as a case study, we show how backbone inference, box decoding, and NMS run entirely on the Chimera GPNPU — no host CPU intervention,

ChiPy: Bridge Neural Networks and C++ on Silicon — Full Inference Pipelines with Zero CPU Round-Trips Read More +

The New Baseline for Human-Centric Devices Starts with Always-On Edge AI Audio: Introducing the Synaptics® Astra™ SR80 Series

This blog post was originally published at Synaptics’ website. It is reprinted here with the permission of Synaptics. The devices we wear, carry, and live with are becoming our most personal AI companions—and that demands they be always aware, always private, and always delivering exceptional audio. The Astra™ SR80 Series delivers always-on Edge AI processing and

The New Baseline for Human-Centric Devices Starts with Always-On Edge AI Audio: Introducing the Synaptics® Astra™ SR80 Series Read More +

What is a Spatial Filter, and How Does it Enhance Depth Quality in ToF Cameras?

This blog post was originally published at e-con Systems’ website. It is reprinted here with the permission of e-con Systems. Time-of-Flight (ToF) cameras generate depth maps by measuring the phase shift between emitted near-infrared light and its reflection. Each pixel records the shift, which is then converted into distance information. But raw depth maps tend to contain

What is a Spatial Filter, and How Does it Enhance Depth Quality in ToF Cameras? Read More +

Designing with Efinix FPGA DSP Blocks

This blog post was originally published at Efinix’s website. It is reprinted here with the permission of Efinix. Today’s most advanced digital signal processing (DSP) solutions demand speed, adaptability, and precision — and that’s exactly where FPGAs (Field-Programmable Gate Arrays) shine. As a powerful hardware platform, FPGAs deliver exceptional parallel processing capability, high configurability, and

Designing with Efinix FPGA DSP Blocks Read More +

Physical AI: 8 Questions Every Engineering Leader Is Asking

This blog post was originally published at Geisel Software’s website. It is reprinted here with the permission of Geisel Software. Jensen Huang called it at CES 2025: “The next frontier of AI is physical.” Since then, the phrase has been everywhere — in investor decks, conference keynotes, and vendor pitches. But for the software engineering managers, directors, VPs, and

Physical AI: 8 Questions Every Engineering Leader Is Asking Read More +

Everything Is Going to Be Driven by Algorithms

This blog post was originally published at Ambarella’s website. It is reprinted here with the permission of Ambarella. A security camera on a warehouse loading dock captures 86,400 seconds of video every day. A fleet telematics recorder on a long-haul truck accumulates gigabytes of road footage between fuel stops. A surgical robot’s stereo cameras generate

Everything Is Going to Be Driven by Algorithms Read More +

Face Super Resolution for Better Video Experiences

This blog post was originally published at Visidon’s website. It is reprinted here with the permission of Visidon. Video has become the primary medium for communication — from hybrid meetings to live events and social media. At the same time, expectations have risen. Faces need to look sharp, expressive, and natural — even when captured from

Face Super Resolution for Better Video Experiences Read More +

Scalable FPGA Prototyping for AI SoCs: Handling Massive Parallelism and Bandwidth

This blog post was originally published at Tessolve’s website. It is reprinted here with the permission of Tessolve. Creating an AI System-on-Chip (SoC) today resembles conducting a thousand musicians playing different melodies at once; each note, or data stream, must align perfectly. As AI workloads become increasingly complex, prototyping these SoCs on FPGA (Field Programmable

Scalable FPGA Prototyping for AI SoCs: Handling Massive Parallelism and Bandwidth Read More +

Falcon Takes Flight: Connect Tech’s Vehicle AI Platform Was Built for the Worst Conditions on Earth

This blog post was originally published at Macnica America’s website. It is reprinted here with the permission of Macnica America. Dust. Vibration. Mud. Sub-zero mornings and scorching afternoons. These are the conditions that kill most compute platforms before they ever reach production, and yet it’s exactly these conditions, on farms, construction sites, and open-pit mines, where

Falcon Takes Flight: Connect Tech’s Vehicle AI Platform Was Built for the Worst Conditions on Earth 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