Search Results for author: Kristína Malinovská

Found 2 papers, 1 papers with code

QuasiNet: a neural network with trainable product layers

no code implementations21 Nov 2023 Kristína Malinovská, Slavomír Holenda, Ľudovít Malinovský

Classical neural networks achieve only limited convergence in hard problems such as XOR or parity when the number of hidden neurons is small.

Controlling the Output of a Generative Model by Latent Feature Vector Shifting

1 code implementation15 Nov 2023 Róbert Belanec, Peter Lacko, Kristína Malinovská

We have trained latent feature shifter for multiple facial features, and outperformed our baseline method in the number of generated images with the desired feature.

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