I am member of a leadership team at Chalmers AI Research Centre (CHAIR), where I organize a series of conferences, workshops and courses on the theme "AI for Scientific Data Analysis".

I have taught four courses on the Master's (M) and Bachelor's (B) level:TIF360 - Advanced Machine Learning (M)FFR105 - Stochastic optimization algorithms (M)SEE095 - Introductory Physics (B)TIF083 - Experimental Physics (B)

My PhD project was in developing deep learning models for nanoplasmonic spectroscopy and nanofluidic microscopy analysis. I utilized deep learning-based computer vision in nanofluidic scattering microscopy, a scattering-based optical microscopy method, to study the properties of nano-sized biological molecules and nanoparticles. Further, I used deep learning to study the response of nanoplasmonic sensors in a catalytic nanoreactor to correlate the effect of complex catalytic nanoparticle surface effects on said particles' catalytic activity, as well as improve the speed and limits of detection of hydrogen gas sensors in the framework of the TechForH2 competence center for hydrogen energy technologies at Chalmers.My thesis, Pushing The Boundaries of Single Molecule Microscopy, Optical Sensing and Mass Spectrometry through Deep Learning, can be found here: https://research.chalmers.se/publication/543241/file/543241_Fulltext.pdf

HP/ECTS/Credits: 357/300

I am co-founder & CTO of start-up iflai, which offers data- and energy efficient AI solutions. We build highly scalable, customizable, reliable and reproducible analysis software based on cutting-edge AI research, with clients in biotech, manufacturing, forestry, security and aerospace.You can reach me at henrik@iflai.com

I help teach the PhD-level course "Advanced Machine Learning Techniques applied to Microscopy Data Analysis" in the mAp Doctoral School of ETH Zürich, and have developed portions of the material and lectures.