Seguir
Jakub Swiatkowski
Jakub Swiatkowski
PhD Student, University of Warsaw
Dirección de correo verificada de mimuw.edu.pl
Título
Citado por
Citado por
Año
How good is the bayes posterior in deep neural networks really?
F Wenzel, K Roth, BS Veeling, J Świątkowski, L Tran, S Mandt, J Snoek, ...
International Conference on Machine Learning (ICML), 37, 2020
1622020
Discriminative k-shot learning using probabilistic models
M Bauer, M Rojas-Carulla, JB Świątkowski, B Schölkopf, RE Turner
2nd Bayesian Deep Learning Workshop, NIPS 2017, 2017
512017
Hydra: Preserving ensemble diversity for model distillation
L Tran, BS Veeling, K Roth, J Swiatkowski, JV Dillon, J Snoek, S Mandt, ...
Uncertainty & Robustness in Deep Learning Workshop, ICML 2020, 2020
242020
The k-tied normal distribution: A compact parameterization of gaussian mean field posteriors in bayesian neural networks
J Swiatkowski, K Roth, B Veeling, L Tran, J Dillon, J Snoek, S Mandt, ...
International Conference on Machine Learning (ICML), 37, 9289-9299, 2020
232020
Improved GQ-CNN: Deep learning model for planning robust grasps
M Jaśkowski, J Świątkowski, M Zając, M Klimek, J Potiuk, P Rybicki, ...
arXiv preprint arXiv:1802.05992, 2018
52018
Continuous Control With Ensemble Deep Deterministic Policy Gradients
P Januszewski, M Olko, M Królikowski, J Świątkowski, M Andrychowicz, ...
arXiv preprint arXiv:2111.15382, 2021
12021
On the Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
J Świątkowski, K Roth, BS Veeling, L Tran, JV Dillon, J Snoek, S Mandt, ...
2019
Bayesian Neural Networks for K-Shot Learning
JB Świątkowski
2017
Three-tier web application for medical clinics
J Świątkowski
Instytut Mikroelektroniki i Optoelektroniki, 2014
2014
Supplementary Materials for: The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
J Swiatkowski, K Roth, BS Veeling, L Tran, JV Dillon, J Snoek, S Mandt, ...
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–10