Algorithms

Introducing NVFP4 for Efficient and Accurate Low-precision Inference

Algorithms, Blog Posts, NVIDIA, Processors, Software, Tools /

This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. To get the most out of AI, optimizations are critical. When developers think about optimizing AI models for inference, model compression techniques—such as quantization, distillation, and pruning—typically come to mind. The most common of the three, without […]

Introducing NVFP4 for Efficient and Accurate Low-precision Inference Read More +

“Computer Vision at Sea: Automated Fish Tracking for Sustainable Fishing,” a Presentation from Tryolabs and the Nature Conservancy

Algorithms, Object Identification, Object Tracking, Software, Summit 2025, Tools, Tryolabs, Videos /

Alicia Schandy Wood, Machine Learning Engineer at Tryolabs, and Vienna Saccomanno, Senior Scientist at The Nature Conservancy, co-present the “Computer Vision at Sea: Automated Fish Tracking for Sustainable Fishing” tutorial at the May 2025 Embedded Vision Summit. What occurs between the moment a commercial fishing vessel departs from shore and… “Computer Vision at Sea: Automated

“Computer Vision at Sea: Automated Fish Tracking for Sustainable Fishing,” a Presentation from Tryolabs and the Nature Conservancy Read More +

Simplifying Vision AI Development with Renesas AI Model Deployer Powered by NVIDIA TAO

Algorithms, Blog Posts, NVIDIA, Processors, Renesas, Software, Tools /

This blog post was originally published at Renesas’ website. It is reprinted here with the permission of Renesas. Edge AI is no longer a futuristic idea—it’s an essential technology driving today’s smart devices across industries, from industrial automation to consumer IoT applications. But building AI applications at the edge still comes with challenges: complexity with

Simplifying Vision AI Development with Renesas AI Model Deployer Powered by NVIDIA TAO Read More +

“Squinting Vision Pipelines: Detecting and Correcting Errors in Vision Models at Runtime,” a Presentation from Squint AI

Algorithms, Software, Squint AI, Summit 2025, Tools, Videos /

Ken Wenger, Chief Technology Officer at Squint AI, presents the “Squinting Vision Pipelines: Detecting and Correcting Errors in Vision Models at Runtime” tutorial at the May 2025 Embedded Vision Summit. As humans, when we look at a scene our first impressions are sometimes wrong; we need to take a second… “Squinting Vision Pipelines: Detecting and

“Squinting Vision Pipelines: Detecting and Correcting Errors in Vision Models at Runtime,” a Presentation from Squint AI Read More +

The Outer Loop: The Real Driver of AI Success

Algorithms, Blog Posts, RapidFire AI, Software, Tools /

This blog post was originally published in expanded form at RapidFire AI’s website. It is reprinted here with the permission of RapidFire AI. When people talk about deep learning, they usually talk about the inner loop—the elegant dance of forward passes, backpropagation, and gradient descent. This is the part that’s been endlessly refined over the

The Outer Loop: The Real Driver of AI Success Read More +

“ONNX and Python to C++: State-of-the-art Graph Compilation,” a Presentation from Quadric

Algorithms, Processors, Quadric, Software, Summit 2025, Tools, Videos /

Nigel Drego, Co-founder and Chief Technology Officer at Quadric, presents the “ONNX and Python to C++: State-of-the-art Graph Compilation” tutorial at the May 2025 Embedded Vision Summit. Quadric’s Chimera general-purpose neural processor executes complete AI/ML graphs—all layers, including pre- and post-processing functions traditionally run on separate DSP processors. To enable… “ONNX and Python to C++:

“ONNX and Python to C++: State-of-the-art Graph Compilation,” a Presentation from Quadric Read More +

Low-power Computer Vision Challenge: Empowering AI Development on Edge Devices

Algorithms, Blog Posts, Processors, Qualcomm, Software, Tools /

This blog post was originally published at Qualcomm’s website. It is reprinted here with the permission of Qualcomm. The Low-Power Computer Vision Challenge (LPCVC) is an annual competition organized by the Institute of Electrical and Electronics Engineers (IEEE) to improve the energy efficiency of computer vision technologies for systems with constrained resources. Established in 2015

Low-power Computer Vision Challenge: Empowering AI Development on Edge Devices Read More +

“Beyond the Demo: Turning Computer Vision Prototypes into Scalable, Cost-effective Solutions,” a Presentation from Plainsight Technologies

Algorithms, Object Identification, Object Tracking, Plainsight Technologies, Software, Summit 2025, Tools, Videos /

Kit Merker, CEO of Plainsight Technologies, presents the “Beyond the Demo: Turning Computer Vision Prototypes into Scalable, Cost-effective Solutions” tutorial at the May 2025 Embedded Vision Summit. Many computer vision projects reach proof of concept but stall before production due to high costs, deployment challenges and infrastructure complexity. This presentation… “Beyond the Demo: Turning Computer

“Beyond the Demo: Turning Computer Vision Prototypes into Scalable, Cost-effective Solutions,” a Presentation from Plainsight Technologies Read More +

“Running Accelerated CNNs on Low-power Microcontrollers Using Arm Ethos-U55, TensorFlow and Numpy,” a Presentation from OpenMV

Algorithms, OpenMV, Processors, Software, Summit 2025, Tools, Videos /

Kwabena Agyeman, President of OpenMV, presents the “Running Accelerated CNNs on Low-power Microcontrollers Using Arm Ethos-U55, TensorFlow and Numpy” tutorial at the May 2025 Embedded Vision Summit. In this presentation, Agyeman introduces the OpenMV AE3 and OpenMV N6 low-power, high-performance embedded machine vision cameras, which are 200x better than the… “Running Accelerated CNNs on Low-power

“Running Accelerated CNNs on Low-power Microcontrollers Using Arm Ethos-U55, TensorFlow and Numpy,” a Presentation from OpenMV Read More +

R²D²: Building AI-based 3D Robot Perception and Mapping with NVIDIA Research

Algorithms, Blog Posts, Multimodal, NVIDIA, Object Identification, Object Tracking, Processors, Robotics, Sensors and Cameras, Software, Tools /

This blog post was originally published at NVIDIA’s website. It is reprinted here with the permission of NVIDIA. Robots must perceive and interpret their 3D environments to act safely and effectively. This is especially critical for tasks such as autonomous navigation, object manipulation, and teleoperation in unstructured or unfamiliar spaces. Advances in robotic perception increasingly

R²D²: Building AI-based 3D Robot Perception and Mapping with NVIDIA Research 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.

Pages

Topics

Contact

Address

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

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