Guillermo Valle Pérez

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 14

Top Topics

Semantic Representations

Top Venues

ACM Trans. Graph.

J. Mach. Learn. Res.

Publications

Ouns El Harzli, Bernardo Cuenca Grau, Guillermo Valle Pérez, Ard A. Louis
Double-Descent Curves in Neural Networks: A New Perspective Using Gaussian Processes. AAAI (2024)
Chris Mingard, Henry Rees, Guillermo Valle Pérez, Ard A. Louis
Do deep neural networks have an inbuilt Occam's razor? CoRR (2023)
Yoann Lemesle, Masataka Sawayama, Guillermo Valle Pérez, Maxime Adolphe, Hélène Sauzéon, Pierre-Yves Oudeyer
Evaluating language-biased image classification based on semantic representations. CoRR (2022)
Yoann Lemesle, Masataka Sawayama, Guillermo Valle Pérez, Maxime Adolphe, Hélène Sauzéon, Pierre-Yves Oudeyer
Language-biased image classification: evaluation based on semantic representations. ICLR (2022)
Chris Mingard, Guillermo Valle Pérez, Joar Skalse, Ard A. Louis
Is SGD a Bayesian sampler? Well, almost. J. Mach. Learn. Res. 22 (2021)
Shuofeng Zhang, Isaac Reid, Guillermo Valle Pérez, Ard A. Louis
Why Flatness Correlates With Generalization For Deep Neural Networks. CoRR (2021)
Guillermo Valle Pérez, Gustav Eje Henter, Jonas Beskow, Andre Holzapfel, Pierre-Yves Oudeyer, Simon Alexanderson
Transflower: probabilistic autoregressive dance generation with multimodal attention. ACM Trans. Graph. 40 (6) (2021)
Guillermo Valle Pérez, Gustav Eje Henter, Jonas Beskow, Andre Holzapfel, Pierre-Yves Oudeyer, Simon Alexanderson
Transflower: probabilistic autoregressive dance generation with multimodal attention. CoRR (2021)
Ouns El Harzli, Guillermo Valle Pérez, Ard A. Louis
Double-descent curves in neural networks: a new perspective using Gaussian processes. CoRR (2021)
Chris Mingard, Guillermo Valle Pérez, Joar Skalse, Ard A. Louis
Is SGD a Bayesian sampler? Well, almost. CoRR (2020)
Guillermo Valle Pérez, Ard A. Louis
Generalization bounds for deep learning. CoRR (2020)
Guillermo Valle Pérez, Chico Q. Camargo, Ard A. Louis
Deep learning generalizes because the parameter-function map is biased towards simple functions. ICLR (Poster) (2019)
Chris Mingard, Joar Skalse, Guillermo Valle Pérez, David Martínez-Rubio, Vladimir Mikulik, Ard A. Louis
Neural networks are a priori biased towards Boolean functions with low entropy. CoRR (2019)
Guillermo Valle Pérez, Chico Q. Camargo, Ard A. Louis
Deep learning generalizes because the parameter-function map is biased towards simple functions. CoRR (2018)