Folgen
Martin Trapp
Martin Trapp
Machine learning researcher, Aalto University
Bestätigte E-Mail-Adresse bei aalto.fi - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Random sum-product networks: A simple and effective approach to probabilistic deep learning
R Peharz, A Vergari, K Stelzner, A Molina, X Shao, M Trapp, K Kersting, ...
Uncertainty in Artificial Intelligence, 334-344, 2020
160*2020
Einsum networks: Fast and scalable learning of tractable probabilistic circuits
R Peharz, S Lang, A Vergari, K Stelzner, A Molina, M Trapp, ...
International Conference on Machine Learning, 7563-7574, 2020
1232020
One million posts: A data set of german online discussions
D Schabus, M Skowron, M Trapp
Proceedings of the 40th international ACM SIGIR conference on research and …, 2017
662017
Uncertainty-guided source-free domain adaptation
S Roy, M Trapp, A Pilzer, J Kannala, N Sebe, E Ricci, A Solin
European conference on computer vision, 537-555, 2022
622022
Bayesian learning of sum-product networks
M Trapp, R Peharz, H Ge, F Pernkopf, Z Ghahramani
Advances in Neural Information Processing Systems (NeurIPS), 2019
532019
Deep Structured Mixtures of Gaussian Processes
M Trapp, R Peharz, F Pernkopf, CE Rasmussen
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
49*2020
AdvancedHMC. jl: A robust, modular and efficient implementation of advanced HMC algorithms
K Xu, H Ge, W Tebbutt, M Tarek, M Trapp, Z Ghahramani
Symposium on Advances in Approximate Bayesian Inference, 1-10, 2020
242020
Periodic activation functions induce stationarity
L Meronen, M Trapp, A Solin
Advances in Neural Information Processing Systems 34, 1673-1685, 2021
212021
Safe Semi-Supervised Learning of Sum-Product Networks
M Trapp, T Madl, R Peharz, F Pernkopf, R Trappl
Conference on Uncertainty in Artificial Intelligence (UAI), 2017
172017
Automatic identification of character types from film dialogs
M Skowron, M Trapp, S Payr, R Trappl
Applied Artificial Intelligence 30 (10), 942-973, 2016
172016
Structure inference in sum-product networks using infinite sum-product trees
M Trapp, R Peharz, M Skowron, T Madl, F Pernkopf, R Trappl
NIPS Workshop on Practical Bayesian Nonparametrics, 2016
162016
Leveraging Probabilistic Circuits for Nonparametric Multi-Output Regression
Z Yu, M Zhu, M Trapp, A Skryagin, K Kersting
Conference on Uncertainty in Artificial Intelligence (UAI), 2021
142021
Fixing overconfidence in dynamic neural networks
L Meronen, M Trapp, A Pilzer, L Yang, A Solin
IEEE/CVF Winter Conference on Applications of Computer Vision, 2680-2690, 2024
112024
Sum-product-transform networks: Exploiting symmetries using invertible transformations
T Pevný, V Smídl, M Trapp, O Poláček, T Oberhuber
International Conference on Probabilistic Graphical Models, 341-352, 2020
112020
DynamicPPL: Stan-like speed for dynamic probabilistic models
M Tarek, K Xu, M Trapp, H Ge, Z Ghahramani
arXiv preprint arXiv:2002.02702, 2020
102020
Grounded word learning on a pepper robot
M Hirschmanner, S Gross, B Krenn, F Neubarth, M Trapp, M Vincze
Proceedings of the 18th International Conference on Intelligent Virtual …, 2018
92018
Transport with Support: Data-Conditional Diffusion Bridges
E Tamir, M Trapp, A Solin
Transactions on Machine Learning Research (TMLR), 2023
82023
Subtractive Mixture Models via Squaring: Representation and Learning
L Loconte, AM Sladek, S Mengel, M Trapp, A Solin, N Gillis, A Vergari
arXiv preprint arXiv:2310.00724, 2023
82023
Characteristic Circuits
Z Yu, M Trapp, K Kersting
Advances in Neural Information Processing Systems 36, 2024
52024
Disentangling model multiplicity in deep learning
A Heljakka, M Trapp, J Kannala, A Solin
arXiv preprint arXiv:2206.08890, 2022
5*2022
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20