RSSAmplifier

Blog

Homepage on Jan Hünermann

Recent content in Homepage on Jan Hünermann

janhuenermann.comRSS feed ↗6 posts

Latest posts

Flash Attention

Much progress in AI over the past few years has been fueled by the transformer architecture. Transformers are the closest thing we have right now to machine learnable programs. They can be trained to generate images , text , videos , audio , video games , or even raw byte sequences , you name it. Behind the transformer, powering many of these applications, there are two key operations which make…

Live in the future

The best startups are founded by ingenious people. I agree with this. But there is another, somewhat more overlooked aspect to great founders. The best founders live in the future. In order to find problems that are yet to be solved, the future is the best place to be. Only when you take for granted what is novel to other people, you are able to assemble the puzzle and look for missing pieces.…

Essay on the neural lace

Imagine a world where artificial general intelligence is a thing, where robots assemble robots, where computers cure cancer, and where everything we do today is automated. In such a robot world, the problems arise with humans – not robots. What is left to do for us, if we are replaced in everything we do today? More importantly, how can computers align with our values, so they work with us and not…

Abstract Art with ML

Randomly initialised neural networks are able to produce visually appealing images. In this post, we explore what compositional pattern producing networks are, how they can be parameterised and what kind of images can be obtained using this technique.

Self-Driving Cars in the Browser

This project demonstrates how a computer can learn by itself how to control a car. Using reinforcement learning, the agent’s neural network is trained to maximize its reward, which in this case is the speed of the car. The code runs in the browser and you can watch the cars drive below.

About

My name is Jan Hünermann and I'm passionate about startups, technology and self-improving algorithms. Currently I'm an Applied Scientist at Wayve, developing Embodied AI to solve autonomous driving. In my free time I like to tinker around with software engineering projects and train deep neural nets. Read more about my projects . Besides that, I am an eager runner, enjoy to chase Alpine peaks, and…