Artificial neural networks (ANNs) make up a significant portion of machine learning and deep learning, ranging from simple, early networks consisting of only a handful of neurons, to more recent networks with hundreds of billions of parameters (e.g., GPT-3). Despite the clear success of ANNs, there is clearly much that we can still learn from biological systems, which have evolved an amazing variety of solutions to solve the same challenges that AI engineers face.
Imagination’s neural network accelerator and Visidon’s denoising algorithm prove to be perfect partners
This blog post is a result of a collaboration between Visidon, headquartered in Finland and Imagination, based in the UK. Visidon is recognised as an expert in algorithms for camera image enhancement and analysis and Imagination has a series of world-beating neural network accelerators (NNA) with performance up to 100 TOPS per second per core. The problem tackled in this blog post is denoising images from conventional colour cameras. The solution is in two parts: 1. Algorithms that remove the noise without damaging image detail. 2. A high-performance convolution engine capable of running a trained neural network that takes a colour image as input and outputs a denoised colour image.
Imagination has been supplying its GPU IP into the automotive sector for over 15 years and has the number one spot for market share for GPUs for application processors. As such is has silicon-proven experience assisting automotive OEMs to build SoCs that conform to the requirement for ASIL B or higher, while also providing the long-term support that is demanded by the industry. This last point is critical. We continue to offer support to solutions that were introduced into the market 10 years ago, as these are still in cars on the road today, and customers can rest assured we will be there in long into the future to support our current IP as well.
Cambridge, one of the most famous cities in England, is well known for many things, such as its ancient university, its classical architecture, punting on its rivers and the myriad bicycles that are the preferred method of transport for its famous students. Beyond academia, it’s also home to a thriving commercial engineering sector – and now Imagination is adding itself to the list of employers in the area.
This year’s International Women in Engineering Day theme is heroes, celebrating the best, brightest and bravest women in engineering. When I was thinking about this, I did what I think most people would do. I thought about famous female engineers that have made their mark; the likes of Hedy Lamarr, Edith Clarke, and Ada Lovelace; trailblazers who changed the world. But while these names have impacted my life, sometimes without me even knowing, my engineering heroes are a little closer to home.
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.
Welcome to the first in a series of articles where we explore how Imagination and Humanising Autonomy, a UK-based behaviour AI company, are teaming up to deliver practical, real-world AI-driven active safety. We have talked at length about the steps that Imagination takes every day to make our world safer with automotive AI. Today we see advanced driver assistance systems (ADAS) that have AI at their core. From simple, dynamic satnav route planning, through lane keep assist, to full autonomous driving stacks, drivers are gradually becoming equipped with more ways than ever to take the stress out of their journeys.
The sun is starting to come out, people are returning to society, and potentially most exciting; we at DevTech are releasing a new version of the PowerVR SDK and Tools. The PowerVR SDK contains not only our graphics development framework, but also a handful of example applications that show you not only how to implement certain techniques, but also make the most out of your PowerVR platforms. Between the modules that help you deploy cross-platform or libraries that let you focus on the actual code rather than boilerplate setup; our SDK has everything you need to hit the ground running with making a high-performance application. We’re starting with the SDK, rather than the tools this time, because this first talking point is a pretty big one, we think.
If you have any enquiries regarding any of our blog posts, please contact:
Tel: +44 (0)1923 260 511
Sign up to receive the latest news and product updates from Imagination straight to your inbox.