Home Page

forweb29
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.

Research

My research interestsRecent research activitiesPublicationsPatents
  • Computer Science in general
  • Computational Intelligence
  • Neural networks (deep learning in current lingo)
  • Random graphs and small world networks
  • Hopfield networks, phase diagrams
  • Critical phenomena
  • Spiking Neural Networks
  • Texture analysis
  • Dynamic systems and fractals
  • Information theory
  • Computer modeling/GPU programming
  • UNIX/Linux/MacOSX administration

  • Creating a large scale predictive vision model incorporating feedback
  • Analysis of network topologies emerging from spiking neural models and other simplified computational models
  • Study of critical systems

Teaching
20132009/2010

Spiking neural networks as a parallel computing paradigm June 2013, six lectures at Faculty of Mathematics and Computer Science, Nicolaus Copernicus University, Toruń

Mathematical Foundations of Neuroscience – winter semester 2009/2010. Preliminary program. Any supplemental material will be published here.
Lecture presentations:

Programs/scripts/animations:

Selected student projects:

Other stuff
Some minor projectsInteresting links
Photos from journeys/conferences etc.

Some of the galleries may take a few minutes to load, depending on the Internet connection speed. Enjoy!

img_2013_12_27_14_52_00_DSC_0527
img_2013_12_26_15_50_02_DSC_0448
img_2013_12_23_14_10_01_DSC_9944
img_2013_12_24_11_50_03_DSC_9988
img_2011_06_30_19_09_02_DSC_4850
img_2010_12_11_17_15_04_DSC_2124
OLYMPUS DIGITAL CAMERA
OLYMPUS DIGITAL CAMERA
DSC_2065
DSC_2221
DSC_2233
DSC_2092
DSC_2271
2016_11_25_13_34_12_DSC_6276
2016_11_25_13_47_26_DSC_6278
Bright stars shine briefly - memory of a friend who died too early
jaitomekTomasz Schreiber, my scientific advisor, collaborator, coauthor, friend. We started working together in 2003, at that time he was already a rising star of polish mathematics. Working with him was always a pleasure. Tomek was a kind of man who had been giving the best, never asking for anything in exchange. Always smiling, full of energy, full of faith in people. He was incredibly bright, with a great sense of humor. He could play with mathematical symbols so cleverly that it sometimes took a few days to understand what he achieved in seconds. When a few years ago Tomek was mourning his advisor, Alexander Nagaev who died in a tragic accident I could not imagine that I’ll be mourning him so soon. In recent years he has been fighting with a fatal disease. But the disease was never an excuse for him. Instead it was something that motivated him to an even harder work. He died on first of December 2010. He was 35. He left his wife, loving family, great students and friends, tens of unfinished mathematical ideas. I will always remember him smiling.

Tomasz Schreiber’s Memorial Session

My memories of Tomek