Detecting and overcoming bias in data with explainable artificial intelligence

Detecting and overcoming bias in data with explainable artificial intelligence

Grant Preludium no. 2019/35/N/ST6/04052

Gdańsk University of Technology

Detecting and overcoming bias in data with explainable artificial intelligence

Descriptors:

  • ST6_11: Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)
  • ST6_7: Artificial intelligence, intelligent systems, multi-agent systems

Panel:

  • ST6 - Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Funding details:

  • Amount awarded: 138 240 PLN
  • Project start date (Y-m-d): 2020-06-19
  • Project end date (Y-m-d): 2023-06-18
  • Project duration:: 36 months (the same as in the proposal)
  • Project status: Pending project

Projects

Last updated on Mar 4, 2022
GEBI
GEBI

Global Explanations for Bias Identification
Last updated on Jun 28, 2022
The (de)biasing effect of GAN-based augmentation methods
The (de)biasing effect of GAN-based augmentation methods

This work explored unconditional and conditional GANs to compare their bias inheritance and how the synthetic data influenced the models. In addition, we examined classification models trained on both real and synthetic data with counterfactual bias explanations.

Meet the Team

Research group

Avatar

Agnieszka Mikołajczyk

Principal Investigator

Explainable Artificial Intelligence, Image Analysis, Deep Learning

Avatar

Michał Grochowski

Supervisor

Publications

Published during grant

A. Mikolajczyk, M. Grochowski, A. Kwasigroch (2021). Towards explainable classifiers using the counterfactual approach-global explanations for discovering bias in data. Journal of Artificial Intelligence and Soft Computing Research.

PDF Cite Code

Z. Klawikowska, A. Mikolajczyk, M. Grochowski (2020). Explainable AI for Inspecting Adversarial Attacks on Deep Neural Networks. International Conference on Artificial Intelligence and Soft Computing.

Cite

Contact

Feel free to contact us