IMG SERIES4 NNA
BEYOND NEXT-GEN AI
The edge platform of choice for assisted driving and full self-driving cars.
A Message About COVID-19 From Imagination Technologies' CMO
We create and license market-leading processor solutions for graphics and vision & AI processing.
Find the ideal SoC solution to give your product a competitive edge.
Imagination’s graphics technology is renowned for offering the most power-efficient designs in the industry, delivering outstanding UI and gaming performance.
Vision and AI
From the devices in our pockets to the cars we drive AI is everywhere. Our neural network accelerators, combined with our powerful software tools, raise the bar for inferencing performance for embedded devices.
Working with Imagination
Join our team
At Imagination Technologies, we apply world-renowned engineering expertise to solve today’s most pressing technology challenges; from smarter devices using artificial intelligence to greater insights through augmented reality.
Create today what the world will enjoy tomorrow.
Technology, news and insights
It’s no exaggeration to say that connectivity is the lifeblood that enables all our everyday tech to function, and that extends to connectivity inside our cars. In this blog post though, we’re not talking about wireless comms for drivers and passengers and their devices. Rather we’re talking about the bus that carries that data internally around the car, enabling all its many components to talk to each other, from the car’s windows to the ESP and ABS systems, to any electronic system that requires input from the driver.
Welcome to the second in a series of articles where we explore how Imagination and Humanising Autonomy, a UK-based AI behaviour company, are teaming up to deliver practical, real-world AI-driven active safety. This time we talk to Ron Pelley, Vice President, Commercial at Humanising Autonomy about their mission, mantras, and the unlikely meeting that started it all.
This article presents a flexible and general optimisation scheme for converting floating-point networks using Variable Bit Depth (VBD) compression as a step towards efficient, low-power inference.