no code implementations • 24 Nov 2022 • Mateusz Olko, Michał Zając, Aleksandra Nowak, Nino Scherrer, Yashas Annadani, Stefan Bauer, Łukasz Kuciński, Piotr Miłoś
In this work, we propose a novel Gradient-based Intervention Targeting method, abbreviated GIT, that 'trusts' the gradient estimator of a gradient-based causal discovery framework to provide signals for the intervention acquisition function.
1 code implementation • NeurIPS 2021 • Marcin Sendera, Jacek Tabor, Aleksandra Nowak, Andrzej Bedychaj, Massimiliano Patacchiola, Tomasz Trzciński, Przemysław Spurek, Maciej Zięba
This makes the GP posterior locally non-Gaussian, therefore we name our method Non-Gaussian Gaussian Processes (NGGPs).
no code implementations • 7 Oct 2021 • Łukasz Maziarka, Aleksandra Nowak, Maciej Wołczyk, Andrzej Bedychaj
One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks.
no code implementations • 22 Jun 2020 • Romuald A. Janik, Aleksandra Nowak
We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a standard gradient-based training.
1 code implementation • 19 Feb 2020 • Romuald A. Janik, Aleksandra Nowak
We perform a massive evaluation of neural networks with architectures corresponding to random graphs of various types.
1 code implementation • 13 Jan 2020 • Andrzej Bedychaj, Przemysław Spurek, Aleksandra Nowak, Jacek Tabor
Independent Component Analysis (ICA) aims to find a coordinate system in which the components of the data are independent.
no code implementations • 1 Mar 2019 • Przemysław Spurek, Aleksandra Nowak, Jacek Tabor, Łukasz Maziarka, Stanisław Jastrzębski
Non-linear source separation is a challenging open problem with many applications.
1 code implementation • 3 Oct 2018 • Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak, Jacek Tabor, Łukasz Struski, Przemysław Spurek
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data.
no code implementations • 27 Sep 2018 • Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak, Jacek Tabor, Łukasz Struski, Przemysław Spurek
We construct a general unified framework for learning representation of structured data, i. e. data which cannot be represented as the fixed-length vectors (e. g. sets, graphs, texts or images of varying sizes).