Zobrazeno 1 - 10
of 103
pro vyhledávání: '"Oesterle, Michael"'
Sparse Autoencoders for transformer-based language models are typically defined independently per layer. In this work we analyze statistical relationships between features in adjacent layers to understand how features evolve through a forward pass. W
Externí odkaz:
http://arxiv.org/abs/2410.08869
For multi-agent reinforcement learning systems (MARLS), the problem formulation generally involves investing massive reward engineering effort specific to a given problem. However, this effort often cannot be translated to other problems; worse, it g
Externí odkaz:
http://arxiv.org/abs/2404.01131
Which set of features was responsible for a certain output of a machine learning model? Which components caused the failure of a cloud computing application? These are just two examples of questions we are addressing in this work by Identifying Coali
Externí odkaz:
http://arxiv.org/abs/2307.09779
Autor:
Oesterle, Michael G.
Publikováno v:
Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses
Thesis (Ph. D.)--University of California, San Diego, 2009.
Title from first page of PDF file (viewed July 9, 2009). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 648-655).
Title from first page of PDF file (viewed July 9, 2009). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 648-655).
Externí odkaz:
http://wwwlib.umi.com/cr/ucsd/fullcit?p3356338
Autor:
Dreher, Simon, Oesterle, Michael-Jörg
Publikováno v:
In Procedia CIRP 2022 107:1355-1360
Autor:
Oesterle, Michael Gerhardt
This thesis presents the results of a study that uses Incremental Dynamic Analysis to assess the seismic performance of steel moment-resisting frames with fluid viscous dampers subjected to earthquake ground motions. The study systematically investig
Externí odkaz:
http://hdl.handle.net/10919/31536
http://scholar.lib.vt.edu/theses/available/etd-03242003-155023/
http://scholar.lib.vt.edu/theses/available/etd-03242003-155023/
Publikováno v:
MIR: Management International Review, 2018 Jan 01. 58(3), 449-464.
Externí odkaz:
https://www.jstor.org/stable/44984660
Autor:
Oesterle, Michael-Jörg, Wolf, Joachim
Publikováno v:
MIR: Management International Review, 2018 Jan 01. 58(2), 361-362.
Externí odkaz:
https://www.jstor.org/stable/44985747
Publikováno v:
In International Business Review April 2018 27(2):367-379
Publikováno v:
In International Business Review October 2016 25(5):1114-1123