Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Douglas Aberdeen"'
Autor:
Jonathan Baxter, Douglas Aberdeen
Publikováno v:
Concurrency and Computation: Practice and Experience. 13:103-119
Generalized matrix–matrix multiplication forms the kernel of many mathematical algorithms, hence a faster matrix–matrix multiply immediately benefits these algorithms. In this paper we implement efficient matrix multiplication for large matrices
Publikováno v:
ICML
Conditional random fields (CRFs) are graphical models for modeling the probability of labels given the observations. They have traditionally been trained with using a set of observation and label pairs. Underlying all CRFs is the assumption that, con
Autor:
Douglas Aberdeen
Publikováno v:
Machine Learning: ECML 2004 ISBN: 9783540231059
ECML
ECML
Reinforcement learning (RL) algorithms attempt to assign the credit for rewards to the actions that contributed to the reward. Thus far, credit assignment has been done in one of two ways: uniformly, or using a discounting model that assigns exponent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a4c590bd79e11bd75fc4b18c2b69e57b
https://doi.org/10.1007/978-3-540-30115-8_6
https://doi.org/10.1007/978-3-540-30115-8_6
Publikováno v:
ACM/IEEE SC 2000 Conference (SC'00).
Artificial neural networks with millions of adjustable parameters and a similar number of training examples are a potential solution for difficult, large-scale pattern recognition problems in areas such as speech and face recognition, classification
Autor:
Jonathan Baxter, Douglas Aberdeen
Publikováno v:
Euro-Par 2000 Parallel Processing ISBN: 9783540679561
Generalised matrix-matrix multiplication forms the kernel of many mathematical algorithms. A faster matrix-matrix multiply immediately benefits these algorithms. In this paper we implement efficient matrix multiplication for large matrices using the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a949641d0897289955518017b807a11
https://doi.org/10.1007/3-540-44520-x_138
https://doi.org/10.1007/3-540-44520-x_138
Autor:
Olivier Buffet, Douglas Aberdeen
Publikováno v:
Artificial Intelligence
Artificial Intelligence, Elsevier, 2009, 173 (5-6), pp.722-747. ⟨10.1016/j.artint.2008.11.008⟩
Artificial Intelligence, 2009, 173 (5-6), pp.722-747. ⟨10.1016/j.artint.2008.11.008⟩
Artificial Intelligence, Elsevier, 2009, 173 (5-6), pp.722-747. ⟨10.1016/j.artint.2008.11.008⟩
Artificial Intelligence, 2009, 173 (5-6), pp.722-747. ⟨10.1016/j.artint.2008.11.008⟩
International audience; We present an any-time concurrent probabilistic temporal planner (CPTP) that includes continuous and discrete uncertainties and metric functions. Rather than relying on dynamic programming our approach builds on methods from s