Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Gispan, Liran"'
Autor:
Greshler, Nir, Eli, David Ben, Rabinovitz, Carmel, Guetta, Gabi, Gispan, Liran, Zohar, Guy, Tamar, Aviv
The combination of Monte Carlo tree search and neural networks has revolutionized online planning. As neural network approximations are often imperfect, we ask whether uncertainty estimates about the network outputs could be used to improve planning.
Externí odkaz:
http://arxiv.org/abs/2406.02103
Predicting not only the target but also an accurate measure of uncertainty is important for many machine learning applications and in particular safety-critical ones. In this work we study the calibration of uncertainty prediction for regression task
Externí odkaz:
http://arxiv.org/abs/1905.11659
Designing a driving policy for autonomous vehicles is a difficult task. Recent studies suggested an end-toend (E2E) training of a policy to predict car actuators directly from raw sensory inputs. It is appealing due to the ease of labeled data collec
Externí odkaz:
http://arxiv.org/abs/1901.00114
Autor:
Levi, Dan1 (AUTHOR) dan.levi@gm.com, Gispan, Liran1 (AUTHOR) giladiniv@gmail.com, Giladi, Niv1,2 (AUTHOR), Fetaya, Ethan3 (AUTHOR) ethan.fetaya@biu.ac.il
Publikováno v:
Sensors (14248220). Aug2022, Vol. 22 Issue 15, p5540-N.PAG. 10p.
Publikováno v:
In Digital Signal Processing September 2017 68:16-23