Our Project

The artificial neural network model was created based on analogies to biological counterparts, such as a simplified model of the neuron or a system of retinal neurons. Due to the increasing complexity of tasks and problems with the development of effective methods for learning deep neural networks, solutions based on algebraic structures dominate Today, advanced approaches in machine learning such as deep learning show a number of undesirable features, such as forgetfulness, susceptibility to adversarial examples, the requirement for a large training set, and slow learning. Most of these features do not occur in biological systems, thus it would be beneficial to take an inspiration from them to help training artificial systems. The aim of the project is to analyze high-level behaviors of biological neural systems and to build innovative artificial models by proposing new paradigms of learning and new architectures of computational models.

Job offers

The Jagiellonian University will run six research groups: Cognitive group (leader Tadeusz Marek), Physics group (leader Maciej A. Nowak), Machine-learning group, Neuro group, BioDataScience group, InfoTech group.

Job offers for

are open.

If you are interested in applying, please fill out the following recruitment form (DOC) or (PDF).

Specific recruitment rules are available here. Declaration on intellectual is available here. The form for processing personal data can be found here.

Business contacts

Seminars Schedule

Maria Lewandowska, "Głębokie konwolucyjne sieci neuronowe do analizy skanów MRI"

Dyskusja na temat danych pochodzących od grupy kongnitywistycznej

Anna Ceglarek i Bartosz Bohaterewicz, "Zastosowanie teorii grafów w analizach fMRI"

Group Workshop

11:00 - 12:00 Machine-learning group
12:10 - 13:10 Physics group
13:10 - 14:00 Lunch
14:00 - 15:00 Neuro group
15:10 - 16:10 Cognitive group
16:10 - 16:40 Coffee Break
16:40 - 18:40 Group Discussion

Localization: Room 1146 (first floor). Faculty of Mathematics and Computer Science, Łojasiewicza 6, 30-348 Kraków.

Maciej Wołczyk, Jacek Tabor, Marek Śmieja, "Biologically-Inspired Spatial Neural Networks"

Romuald Janik, "Explaining the Human Visual Brain 2019 competition and workshop"
Additional information: Paper you can find here.

Magda Gawłowska, "EEG 101"

Igor Podolak, "BioNN machine learning"

11:00 - 13:00 Gabriela Mochol: Prefrontal cortex represents heuristics that
shape choice bias and its integration into future behavior

Localization: online meeting

11:00 - 13:00 Bartosz Bohaterewicz: Machine learning based identification
of suicidal risk in patients diagnosed with schizophrenia,
bases on multi-level resting state fmri features,
semantic development, and cognitive control

Localization: online meeting

11:00 - 13:00 Andrew Saxe: Deep learning theories of perceptual learning,
semantic development, and cognitive control

Localization: online meeting

11:00 - 13:00 Aleksandra Nowak: Neural Networks on Random Graphs

Localization: online meeting

14:00 - 15:00 Daniel Martin: Inferring interactions from all-optical interrogation of neural circuits

Localization: online meeting

11:15 - 12:00 Maciej Wołczyk, Marek Śmieja, Jacek Tabor: Wstęp do "conditional computations"
12:00 - 12:45 Jacek Grela “Uczenie sieci neuronowych jako przejście fazowe”

Localization: online meeting

Group Workshop

10:00 - 11:00 Jacek Rogala: “Sztuczne sieci neuronowe z perspektywy biologa”
11:00 - 12:00 Daniel Wójcik “Równania Hodgkina-Huxleya - mechanizmy generacji iglicy”
12:00 - 13:30 Lunch
13:30 - 14:30 Tomasz Trzciński "Przegląd propozycji mini-projektów w grupie InfoTech"
14:30 - 15:30 Magda Gawłowska "Aktualne trendy w analizie danych EEG"
15:30 - 16:00 Jacek Tabor: dyskusja

Localization: online meeting

Marek Śmieja, "Direct Feedback Alignment"

Group Workshop

11:00 - 12:00 Przemysław Spurek: Independent Component Analysis
12:00 - 13:00 Lunch
13:00 - 14:30 Paweł Hottowy: Perspektywy budowy zaawansowanego implantu dla niewidomych
14:30 - 15:30 Coffee Break: Room 1103
15:30 - 17:00 Daniel Wójcik: Wstęp do neurobiologii obliczeniowej, cz. 1: Równanie kabla - dendryty bierne

Localization: Room 1016 (first floor). Faculty of Mathematics and Computer Science, Łojasiewicza 6, 30-348 Kraków.

Igor Sieradzki, Maciej Wołczyk: Continual Machine Learning: Scenarios, Current Methods and Evaluation

Group Workshop

12:00 - 14:00 Igor Podolak, Igor Sieradzki, Maciej Wołczyk: Introduction to continual learning
14:00 - 14:45 Lunch
14:45 - 15:30 Tomasz Trzciński: Learning binary representaiton of images
15:30 - 16:15 Paweł Oświęcimka: Fractal approach to time series analysis
16:15 - 16:45 Coffee break
16:45 - 17:30 Ziemowit Sławiński: Spiking neural networks

Localization: Room 1146 (first floor). Faculty of Mathematics and Computer Science, Łojasiewicza 6, 30-348 Kraków.

Igor Podolak: Biological blueprints for next generation AI systems
Dyskusja na temat danych pochodzących od grupy kongnitywistycznej - kontynuacja

Title 1

Abstract: ...

Title 2 with link

Abstract: ...

Meet Our Team

prof. Tadeusz Marek

Team Leader

dr Magdalena Fąfrowicz

Research Senior

dr Magda Gawłowska

Research Junior

Bartosz Bohaterewicz

Research Assistant

Anna Ceglarek

Research Assistant

Natalia Golonka

PhD Student

Anna Sobczak

PhD Student

Aleksandra Żyrkowska

PhD Student

prof. Maciej A. Nowak

Team Leader

prof. Romuald Janik

Research Senior

dr Jacek Grela

Research Junior

dr Przemysław Witaszczyk

Research Junior

dr hab. Igor Podolak

Team Leader

dr Łukasz Struski

Research Junior

dr Marek Śmieja

Research Junior

Aleksandra Nowak

PhD Student

Igor Sieradzki

PhD Student

Maciej Wołczyk

PhD Student

prof. Daniel Wójcik

Team Leader

Ziemowit Sławiński

PhD Student

dr hab. inż. Tomasz Trzciński

Team Leader

dr Karol Jerzy Piczak

Research Junior

dr Bartosz Zieliński

Research Senior

Witold Oleszkiewicz

PhD Student

dr hab. inż. Paweł Oświęcimka

Team Leader

Contact Us

ul. prof. Stanisława Łojasiewicza 6
30-348 Kraków
Poland

bionn@matinf.uj.edu.pl

Follow us on

© Copyright, All Rights Reserved.
Designed by BootstrapMade.com