Maciej Wielgosz

Cognitive Computing Researcher

Menu
Close
  • Teaching
  • About me
  • Publications
Resources

Primitives Dataset

A small dataset consisting of short video clips, each containing one of six shapes (cone, cube, cylinder, monkey, sphere, torus) on a black background.

Photo by Ümit Yıldırım
GAN
Ideas
neural-symbolic
RL

GARRET: Generative AdveRsarial Rules ExTractor

What is needed so that robots can work along with humans? Humans fear the unknown. Contemporary Artificial Intelligence (AI) systems have no way to directly incorporate any of the rules known to humans. Those two issues could be overcome if a way to extract, review, and update the rules governing the AI behavior existed. 

Photo by Fleur Treurniet
Resources

Machine Learning Primer

In the course of preparing several ML-related courses, I compiled a short handout containing useful things to know (and hard to find in one place) when entering into Machine Learning (and especially Deep Learning) field, and how to avoid common pitfalls. Its format is inspired by Cornell's note-taking method, containing short questions and (slightly longer) answers, with additional space left for the summary/notes.

Photo by Stéphane Juban
Concept papers
GRU
syncope

Falls prediction in elderly people using Gated Recurrent Units

Falls prevention, especially in older people, becomes an increasingly important topic in the times of aging societies. In this short concept paper, based on Marcin Radzio’s master’s thesis, we present Gated Recurrent Unit-based neural networks models designed for predicting falls (syncope). The cardiovascular systems signals used in the study come…

  • Privacy Policy
  • ORCiD
  • Publons
  • ArXiv
  • Google Scholar
  • LinkedIn
  • Bitbucket
  • Email

Copyright © 2023 Maciej Wielgosz

This website uses cookies. By continuing we assume your permission to deploy cookies, as detailed in our Privacy Policy.