Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Siskind, Jeffrey M"'
Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for such tasks
Externí odkaz:
http://arxiv.org/abs/1809.09318
The navigation problem is classically approached in two steps: an exploration step, where map-information about the environment is gathered; and an exploitation step, where this information is used to navigate efficiently. Deep reinforcement learning
Externí odkaz:
http://arxiv.org/abs/1802.02274
Autor:
Siskind, Jeffrey M.
This thesis proposes a computational model of how children may come to learn the meanings of words in their native language. The proposed model is divided into two separate components. One component produces semantic descriptions of visually observed
Externí odkaz:
http://hdl.handle.net/1721.1/6784
Publikováno v:
Department of Electrical and Computer Engineering Technical Reports
Current implementations of automatic differentiation are far from automatic. We survey the difficulties encountered when applying four existing AD systems, ADIFOR, TAPENADE, ADIC, and FADBAD++, to two simple tasks, minimax optimization and control of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______540::778f445aaf1470388fe0bf7033c150ed
http://docs.lib.purdue.edu/ecetr/368
http://docs.lib.purdue.edu/ecetr/368
Publikováno v:
Department of Electrical and Computer Engineering Technical Reports
We exhibit an aggressive optimizing compiler for a functionalprogramming language which includes a first-class forward automatic differentiation (AD) operator. The compiler’s performance is competitive with FORTRAN-based systems on our numerical ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______540::ee644ee1f86fe5a7e390006708e9aa53
http://docs.lib.purdue.edu/cgi/viewcontent.cgi?article=1368&context=ecetr
http://docs.lib.purdue.edu/cgi/viewcontent.cgi?article=1368&context=ecetr
Autor:
Siskind, Jeffrey M.1, Sherman Jr., James J.2 shermanj@umd.edu, Pollak, Iiya1 ipollak@ecn.purdue.edu, Harper, Mary P.1, Bouman, Charles A.1 bouman@ecn.purdue.edu
Publikováno v:
IEEE Transactions on Pattern Analysis & Machine Intelligence. Sep2007, Vol. 29 Issue 9, p1504-1519. 16p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.