Search Results for author: Mateusz Opala

Found 3 papers, 2 papers with code

Aligned Contrastive Predictive Coding

1 code implementation24 Apr 2021 Jan Chorowski, Grzegorz Ciesielski, Jarosław Dzikowski, Adrian Łańcucki, Ricard Marxer, Mateusz Opala, Piotr Pusz, Paweł Rychlikowski, Michał Stypułkowski

We investigate the possibility of forcing a self-supervised model trained using a contrastive predictive loss to extract slowly varying latent representations.

A Bayesian Nonparametrics View into Deep Representations

no code implementations NeurIPS 2020 Michał Jamroż, Marcin Kurdziel, Mateusz Opala

Specifically, we leverage Bayesian nonparametrics to construct models of neural activations in Convolutional Neural Networks (CNNs) and latent representations in Variational Autoencoders (VAEs).

Memorization

Cannot find the paper you are looking for? You can Submit a new open access paper.