How to bring AI to your manufacturing company
It’s time to share our own AI story.
We started using artificial intelligence (AI) — or machine learning (ML), to be more precise — in 2016. My co-founder Patrick Bleiziffer was still PostDoc at the ETH in Zurich at that time. Since then, we published on ML in scientific journals. See for instance Patrick’s highly cited paper on “Machine Learning of Partial Charges Derived from High-Quality Quantum-Mechanical Calculations”.
In our spare time, we read books and papers on the subject. More importantly, we started writing ML code routinely. We learned from tutorials and started to implement ML in our own applications.
During my PhD thesis I wrote code mostly in Matlab and in C (and derivatives of it). But that was also a few years ago. Nevertheless I have kept working knowledge of it over the years. And hey: a for-loop is a for-loop, isn’t it?
So I dived more and more into the Python AI world on evenings and weekends. And as always, when I discover a new world: I was fascinated. I felt the same fascination as when I started studying chemistry, only to find out later that I was also very interested in physics. And computer science.
But above all I understood one thing: We are on the verge of a new age — the age of AI.
In the coming weeks, I will share what we think it takes to introduce ML in industrial environments, to build it up, and to successfully transfer it into productive systems. If you’ve already done all that: Congratulations! I’m looking forward to your success story!
Our writing is aimed at representatives of high-tech companies that are on their way to making their manufacturing company ready for the AI world. They may be very small companies. Or hidden champions.
We want to share our experience to get you further along the way, especially if you might not want to afford dedicated IT specialists. We think it can be done with limited budget as well. Because we have seen that many of the success factors require soft skills and the will to change. Technology is only one side of the ML coin.
Interested? Stay tuned and follow us on Medium as we unfold what we learned on our industrial AI journey.
Further reading
This is the first article in our series on industrial artificial intelligence (AI). More articles in this series (list updated on release):
(1) How to bring AI to your manufacturing company
(2) Get machine-readable data for industrial AI
(3) Build sandboxes and let them play
(4) Problems you can solve with ML in your company
(5) Your route to success in industrial AI: Think big, start simple
(6) From pilot to maintainable AI technology stack
(7) What you can learn from your smartphone for industrial AI