data_about_players: By default, players_all now covers players mentioned in the paper...
[gostyle.git] / tex / gostyle.bib
blob6f3a4ebbf6b80e9d46c65689c971cb29485f2235
1 % This file was created with JabRef 2.6b2.
2 % Encoding: UTF-8
4 @INPROCEEDINGS{GellySilver2008,
5 author = {Gelly, Sylvain and Silver, David},
6 title = {Achieving master level play in 9x9 computer go},
7 booktitle = {AAAI'08: Proceedings of the 23rd national conference on Artificial
8 intelligence},
9 year = {2008},
10 pages = {1537--1540},
11 publisher = {AAAI Press},
12 abstract = {The UCT algorithm uses Monte-Carlo simulation to estimate the value
13 of states in a search tree from the current state. However, the first
14 time a state is encountered, UCT has no knowledge, and is unable
15 to generalise from previous experience. We describe two extensions
16 that address these weaknesses. Our first algorithm, heuristic UCT,
17 incorporates prior knowledge in the form of a value function. The
18 value function can be learned offline, using a linear combination
19 of a million binary features, with weights trained by temporal-difference
20 learning. Our second algorithm, UCT-RAVE, forms a rapid online generalisation
21 based on the value of moves. We applied our algorithms to the domain
22 of 9 × 9 Computer Go, using the program MoGo. Using both heuristic
23 UCT and RAVE, MoGo became the first program to achieve human master
24 level in competitive play.},
25 isbn = {978-1-57735-368-3},
26 location = {Chicago, Illinois}
29 @BOOK{Jolliffe1986,
30 title = {Principal Component Analysis},
31 publisher = {Springer, New York},
32 year = {1986},
33 author = {I.T. Jolliffe},
34 owner = {hellboy}
37 @INPROCEEDINGS{Riedmiller1993,
38 author = {Martin Riedmiller and Heinrich Braun},
39 title = {A Direct Adaptive Method for Faster Backpropagation Learning: The
40 RPROP Algorithm},
41 booktitle = {IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS},
42 year = {1993},
43 pages = {586--591},
44 owner = {hellboy},
45 timestamp = {2010.03.07}
48 @ARTICLE{MDP,
49 author = {Zito Tiziano and Wilbert Niko and Wiskott Laurenz and Berkes Pietro},
50 title = {Modular toolkit for Data Processing (MDP): a Python data processing
51 framework},
52 journal = {Frontiers in Neuroinformatics},
53 year = {2008},
54 volume = {2},
55 abstract = {Modular toolkit for Data Processing (MDP) is a data processing framework
56 written in Python. From the user's perspective, MDP is a collection
57 of supervised and unsupervised learning algorithms and other data
58 processing units that can be combined into data processing sequences
59 and more complex feed-forward network architectures. Computations
60 are performed efficiently in terms of speed and memory requirements.
61 From the scientific developer's perspective, MDP is a modular
62 framework, which can easily be expanded. The implementation of new
63 algorithms is easy and intuitive. The new implemented units are then
64 automatically integrated with the rest of the library. MDP has been
65 written in the context of theoretical research in neuroscience, but
66 it has been designed to be helpful in any context where trainable
67 data processing algorithms are used. Its simplicity on the user's
68 side, the variety of readily available algorithms, and the reusability
69 of the implemented units make it also a useful educational tool.},
70 doi = {10.3389/neuro.11/008.2008},
71 issn = {ISSN 1662-5196},
72 owner = {hellboy},
73 timestamp = {2010.03.05}
76 @comment{jabref-meta: selector_publisher:}
78 @comment{jabref-meta: selector_author:}
80 @comment{jabref-meta: selector_journal:}
82 @comment{jabref-meta: selector_keywords:}