Multilayer perceptrons (MLP) in Computer Vision

In this blog post, we review the V-MLP literature, compare V-MLPs to CNNs and ViTs, and attempt to extract the ingredients that really matter for efficient and accurate deep learning-based computer vision.

Transformers in Computer Vision

Convolutional Neural Networks (CNN) have been dominant in Computer Vision applications for over a decade. Today, they are being outperformed and replaced by Vision Transformers (ViT) with a higher learning capacity. The fastest ViTs are essentially a CNN/Transformer hybrid, combining the best of both worlds.

An Interview with Marian Verhelst, Axelera AI’s Scientific Advisor

An Interview with Marian Verhelst, Axelera AI’s Scientific Advisor.
I met Marian Verhelst in the summer of 2019 and she immediately stroke me with her passion and competence for computing architecture design. We started immediately a collaboration and today she’s here with us sharing her insights on the future of computing.