Insights and Trends in Machine Learning
or Computer Vision

Read all about our unique quantization techniques that obsolete model retraining & enable the most powerful and energy-efficient AI accelerators.

Vision AI can make access control less invasive. AI accelerators can increase verification speed in AI Access Control without increasing false positives in security.

Open standards enable developers to more easily harness the power of AI accelerators, especially in heterogenous computing. Here you can read in detail why and how we implemented OpenCL using oneAPI on Metis.

At this year’s World Economic Forum in Davos, the spotlight was firmly placed on artificial intelligence (AI), reflecting its growing importance across various sectors. The discussions not only highlighted AI’s expansive role but also emphasized the evolving trend of edge computing, driven by specialized hardware accelerators.

On Labor Day, a day dedicated to celebrating the achievements and perseverance of the workforce, we find ourselves on the cusp of a new era where artificial intelligence (AI) is poised to transform the labor market.

The Metis AI Platform is a one-of-a-kind holistic hardware and software solution establishing best-in-class performance, efficiency, and ease of use for AI inferencing of computer vision workloads at the Edge.

Stephen Owen, Axelera AI Advisor, is an experienced Board Level International Executive with over 16 years of executive-level experience in an S&P Top 500 Semiconductor Company and extensive global leadership and organizational expertise.

RISC-V is inevitable – it became the mantra of RISC-V, and it’s true. But before we see why that is, let’s step back and discuss what RISC-V is and why we should care.

Imagine a world where computing power reaches a historic practical equivalent of two human brains. In this blog article by our Director of Systems Software, Cristian Olar explores how our revolutionary Metis AIPU achieves a remarkable 200 TOPS result at a fraction of today’s costs.

This blog introduces the transformer encoder and decoder architecture and discusses the challenges in inferring them on an edge device: high computational cost, high peak memory requirements, low arithmetic intensity.