The advent of generative models such as DALL-E, Midjourney or Stable Diffusion have brought a deluge of AI-generated images. The question we want to answer is: How to harness their power for innovative uses that improve quality of life? 

We will present two practical examples on how to use generative AI for improving datasets for machine learning. 

Lukáš will show us how to use AI for annotation and labeling of large datasets, while Igor has developed novel ways to generate fingerprints for training fast, accurate models for fragmented fingerprints. In both cases, AI is helping improve the accuracy of models that then help automate administrative processes or even solve crimes.

_Supported by



Lukáš Hudec

Lukáš Hudec


Lukáš Hudec is an AI Architect/Lead Researcher at Cognexa, Researcher/Lecturer at Faculty of Informatics and Information Technologies STU and IPC member of CESCG. He focuses on research of novel methods of deep learning with focus on image processing, analysis, and generation. He applies his research in histology, natural textures, and other industrial domains. His passion is generative models and large-scale multilayered microscopy images.

Igor Jánoš

Igor Jánoš


Igor is an Image Data Synthesis Lead at Innovatrics, designing and testing image synthesis algorithms to improve biometric datasets. He’s also a teaching assistant at Faculty of Informatics and Information Technologies at Slovak University of Technology in Bratislava, where he’s teaching neural networks.


Language: English

5:00 pm
5:10 pm
Presentation – Generative Models for Creation of Annotated Datasets - Lukáš Hudec (Cognexa)
5:40 pm
Presentation – Fine-tuning neural networks to create high quality synthetic fingerprints is not as easy as it seems - Igor Jánoš (Innovatrics)
6:10 pm
Live Q&A – _Slido #better_ai

_Sign up

Past Meetups