Home Page

Filip Piękniewski, PhD
San Diego, CA
e-mail: email

Polish Version pl

I’m a researcher working on computer vision and AI. My main research objective is to introduce dynamics into machine learning which is currently dominated by statistics. Having dynamics is necessary for ML models to produce true understanding of physical reality. My recent attempt to build a machine learning system that naturally incorporates time, online processing and unsupervised learning of the physics is described here (github code here). Until dynamics is deeply incorporated in machine learning models, they will remain “statistical machines” that “statistically work” which is not enough for a real world application such as robotics. My long term ambition is to address Moravec’s Paradox. You may read more in my blog on machine learning and other things.