Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Bojarski, Mariusz"'
Autor:
Bojarski, Mariusz, Chen, Chenyi, Daw, Joyjit, Değirmenci, Alperen, Deri, Joya, Firner, Bernhard, Flepp, Beat, Gogri, Sachin, Hong, Jesse, Jackel, Lawrence, Jia, Zhenhua, Lee, BJ, Liu, Bo, Liu, Fei, Muller, Urs, Payne, Samuel, Prasad, Nischal Kota Nagendra, Provodin, Artem, Roach, John, Rvachov, Timur, Tadimeti, Neha, van Engelen, Jesper, Wen, Haiguang, Yang, Eric, Yang, Zongyi
Four years ago, an experimental system known as PilotNet became the first NVIDIA system to steer an autonomous car along a roadway. This system represents a departure from the classical approach for self-driving in which the process is manually decom
Externí odkaz:
http://arxiv.org/abs/2010.08776
The unsupervised image-to-image translation aims at finding a mapping between the source ($A$) and target ($B$) image domains, where in many applications aligned image pairs are not available at training. This is an ill-posed learning problem since i
Externí odkaz:
http://arxiv.org/abs/1802.06869
Autor:
Bojarski, Mariusz, Yeres, Philip, Choromanska, Anna, Choromanski, Krzysztof, Firner, Bernhard, Jackel, Lawrence, Muller, Urs
As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead. PilotNet is trained using road images paired with the stee
Externí odkaz:
http://arxiv.org/abs/1704.07911
Autor:
Bojarski, Mariusz, Choromanska, Anna, Choromanski, Krzysztof, Firner, Bernhard, Jackel, Larry, Muller, Urs, Zieba, Karol
This paper proposes a new method, that we call VisualBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convolutional neural network (CNN). The method heavily hinges on exploring the intui
Externí odkaz:
http://arxiv.org/abs/1611.05418
Autor:
Bojarski, Mariusz, Choromanska, Anna, Choromanski, Krzysztof, Fagan, Francois, Gouy-Pailler, Cedric, Morvan, Anne, Sakr, Nourhan, Sarlos, Tamas, Atif, Jamal
We consider an efficient computational framework for speeding up several machine learning algorithms with almost no loss of accuracy. The proposed framework relies on projections via structured matrices that we call Structured Spinners, which are for
Externí odkaz:
http://arxiv.org/abs/1610.06209
We analyze the performance of the top-down multiclass classification algorithm for decision tree learning called LOMtree, recently proposed in the literature Choromanska and Langford (2014) for solving efficiently classification problems with very la
Externí odkaz:
http://arxiv.org/abs/1605.05223
Autor:
Bojarski, Mariusz, Del Testa, Davide, Dworakowski, Daniel, Firner, Bernhard, Flepp, Beat, Goyal, Prasoon, Jackel, Lawrence D., Monfort, Mathew, Muller, Urs, Zhang, Jiakai, Zhang, Xin, Zhao, Jake, Zieba, Karol
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to driv
Externí odkaz:
http://arxiv.org/abs/1604.07316
Autor:
Choromanska, Anna, Choromanski, Krzysztof, Bojarski, Mariusz, Jebara, Tony, Kumar, Sanjiv, LeCun, Yann
We consider the hashing mechanism for constructing binary embeddings, that involves pseudo-random projections followed by nonlinear (sign function) mappings. The pseudo-random projection is described by a matrix, where not all entries are independent
Externí odkaz:
http://arxiv.org/abs/1511.05212
We consider supervised learning with random decision trees, where the tree construction is completely random. The method is popularly used and works well in practice despite the simplicity of the setting, but its statistical mechanism is not yet well
Externí odkaz:
http://arxiv.org/abs/1410.6973
Autor:
Bojarski, Mariusz, Choromanska, Anna, Choromanski, Krzysztof, Fagan, Francois, Gouy-Pailler, Cedric, Morvan, Anne, Sakr, Nourhan, Sarlos, Tamas, Atif, Jamal
Publikováno v:
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017)
20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017)
20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), Apr 2017, Fort Lauderdale, Florida, United States. pp.1020-1029
20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017)
20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), Apr 2017, Fort Lauderdale, Florida, United States. pp.1020-1029
We consider an efficient computational framework for speeding up several machine learning algorithms with almost no loss of accuracy. The proposed framework relies on projections via structured matrices that we call Structured Spinners, which are for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c11b577e8c4e7bc028f25e412613c7ad
https://hal.archives-ouvertes.fr/hal-02010086
https://hal.archives-ouvertes.fr/hal-02010086