A few days ago, DeepMind announced their release of NFNets, a family of image classification models that are: State of the art on ImageNet (86.5% top-1 without extra data) Up to 8.7x faster to train than EfficientNets to a given accuracy Normalizer-free (no BatchNorm!) Paper: http://dpmd.ai/06171 Code: http://dpmd.ai/nfnets Has more than 438.4 million parameters The… Les mer

A lot has been written and said about digitalisation. And one can expect that more will be written, and even more will be said. Talkers, writers and doers – all are needed simultaneously, some probably more than others. So, what is it with digitalisation? My own brain-exploding realisation was triggered by the term “Digital Divide”… Les mer

Eighteen years ago, after the summer of 2002, I started a very exciting journey into the world of Artificial Intelligence. It was August the 19th, a Monday in the year 2002 when at 07:00 I started taking my first class in the Faculty of Physics and Artificial Intelligence of the University of Veracruz. Last week,… Les mer

C is a powerful and amazingly fast programming language. Still, the most impressive feature it has is the ability and the speed it can empty a room full of developers when who-take-the-decisions says: “… and it must be coded in C!” I honestly don’t understand this “fear” of C and why universities are adopting other… Les mer

My name is Hugo, and I have a long journey “coding the possible and also the impossible” already behind me. So, I decided to tell my story and adventures using programming languages to touch upon various impressions and learnings but trying not to judge what is better or worst. Tricks, insights, good and bad practices… Les mer