SHOGUN  4.0.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Groups Pages
CONTRIBUTIONS.md
Go to the documentation of this file.
1 Individual Contributions {#contributions}
2 ========================
3 
4 ## Histogram
5 Let the numbers speak: number of commits per developer, cut-off at 50 (last updated: 9. Nov 2014)
6 
7  $ git log --format='%aN' | sort | uniq -c | sort -nr
8 
9  4325 Soeren Sonnenburg
10  2280 Heiko Strathmann
11  1546 Sergey Lisitsyn
12  690 Viktor Gal
13  560 Sebastian Henschel
14  358 Fernando Iglesias
15  265 iglesias
16  265 Gunnar Raetsch
17  226 Shashwat Lal Das
18  218 Chiyuan Zhang
19  213 Thoralf Klein
20  177 lambday
21  165 Evgeniy Andreev
22  150 Wu Lin
23  141 Jonas Behr
24  134 Baozeng Ding
25  129 Parijat Mazumdar
26  116 Christian Widmer
27  96 Abhijeet
28  85 Fabio De Bona
29  83 puffin444
30  82 Roman Votyakov
31  77 tklein23
32  74 khalednasr
33  69 Kevin
34  57 Alesis Novik
35  56 D. Lehmann
36 
37 ## Google Summer of Code Projects
38 We greatly appreciate the support by Google and the hard work of our students and mentors!
39 
40 ### 2014
41  * OpenCV Integration and Computer Vision Applications [Abhijeet Kislay; Kevin Hughes]
42  * Large-Scale Multi-Label Classification [Abinash Panda; Thoralf Klein]
43  * Large-scale structured prediction with approximate inference [Jiaolong Xu; Shell Hu]
44  * Essential Deep Learning Modules [Khaled Nasr; Sergey Lisitsyn, Theofanis Karaletsos]
45  * Fundamental Machine Learning: decision trees, kernel density estimation [Parijat Mazumdar ; Fernando Iglesias]
46  * Shogun Missionary & Shogun in Education [Saurabh Mahindre; Heiko Strathmann]
47  * Testing and Measuring Variable Interactions With Kernels [Soumyajit De; Dino Sejdinovic, Heiko Strathmann]
48  * Variational Learning for Gaussian Processes [Wu Lin; Heiko Strathmann, Emtiyaz Khan]
49 
50 ### 2013
51  * Gaussian Processes for binary classification [Roman Votjakov]
52  * Sampling log-determinants for large sparse matrices [Soumyajit De]
53  * Metric Learning via LMNN [Fernando Iglesias]
54  * Independent Component Analysis (ICA) [Kevin Hughes]
55  * Hashing Feature Framework [Evangelos Anagnostopoulos]
56  * Structured Output Learning [Hu Shell]
57  * A web-demo framework [Liu Zhengyang]
58 
59 ### 2012
60  * Kernel Hypothesis Testing [Heiko Strathmann]
61  * Latent SVM [Viktor Gal]
62  * Multitask Learning [Sergey Listsyn]
63  * Bundle Methods [Michal Uricar]
64  * Multiclass methods [Chiyuan Zhang]
65  * Gaussian Process regression [Jacob Walker]
66  * Structured Output Framework [Fernando Iglesias]
67 
68 ### 2011
69  * Support for new languages [Baozeng Ding]
70  * Dimensionality reduction algorithms [Sergey Lisitsyn]
71  * Streaming / Online Feature Framework [Shashwat Lal Das]
72  * Model selection framework [Heiko Strathmann]
73  * Gaussian Mixture Models [Alesis Novik]
74 
75 ## Individual contributions
76 Alex J. Smola
77  * the pr_loqo optimizer
78 
79 Antoine Bordes
80  * LaRank
81 
82 Thorsten Joachims
83  * SVMLight
84 
85 Chih-Chung Chang and and Chih-Jen Lin
86  * LibSVM
87 
88 Xiang-Rui Wang and Chih-Jen Lin
89  * LIBLINEAR
90 
91 Thomas Serafini, Luca Zanni, Gaetano Zanghirati
92  * the Gradient Projection Decomposition Technique (GPDT) - SVM
93 
94 Vikas Sindhwani
95  * SVM-lin: Fast SVM Solvers for Supervised and Semi-supervised Learning
96 
97 Vojtech Franc
98  * Generalized Nearest Point Problem Solver based L2 (slacks) SVM
99  * Optimized Cutting Plane Support Vector Machines (Ocas)
100 
101 Jean-Philippe Vert and Hiroto Saigo
102  * Local Alignment Kernel
103 
104 Leon Bottou
105  * Stochastic Gradient Descent (SGD) SVM
106 
107 Marius Kloft
108  * 2-norm and q-norm MKL
109  * SMO based true Multi-Class SVM
110 
111 Alexander Zien
112  * Newton based q-norm MKL
113  * POIM code for WD kernels
114 
115 Christian Gehl
116  * Distance Metrics
117 
118 Christian Widmer
119  * Dual and Multitask Learning
120  * Serialization support
121 
122 Jonas Behr
123  * Structured Learning
124 
125 Elpmis Lee
126  * Translation of the documentation to Chinese
127 
128 Baozeng Ding
129  * Support for modular java, c#, ruby, lua interfaces
130 
131 Shashwat Lal Das
132  * Streaming / Online Feature Framework for SimpleFeatures, SparseFeatures, StringFeatures, SGD-QN, Online SGD, Online Liblinear, Online Vowpal Vabit
133 
134 Heiko Strathmann
135  * Model selection/Cross-validation for arbitrary Machines
136  * Statistics module
137  * Subset support in features
138  * Various bugfixes and structural improvements
139  * Serialization improvements and fixes/ Migration framework
140  * Machine Locking for precomputed kernel matrices
141  * Statistical hypothesis testing framework / Kernel Two-Sample/Independence tests
142 
143 Alesis Novik
144  * Gaussian Mixture Models
145 
146 Evgeniy Andreev:
147  * FibonacciHeap
148  * Python 3 support
149  * CoverTree
150  * HashSet
151 
152 Justin Patera
153  * Ruby examples
154 
155 Daniel Korn
156  * C# examples
157 
158 Fernando José Iglesias Garcia
159  * Generic multiclass OvO training
160  * Quadratic Discriminant Analysis
161  * Metric Learning via LMNN
162 
163 J. Liu, S. Ji and J. Ye
164  * SLEP: A Sparse Learning Package C and ported code
165 
166 J. Zhou, J. Chen and J. Ye
167  * MALSAR: Multi-tAsk Learning via StructurAL Regularization ported code
168 
169 
170 We also acknowledge support from Alexander Binder, Alexander Zien, Andre Noll, Cheng Soon Ong, Christian Gehl, Christian Widmer, Christoph Lampert, Fabio De Bona, Jonas Behr, Konrad Rieck, Mikio Braun, Torsten Werner, Vojtech Franc, Yaroslav Halchenko
double norm(double *v, double p, int n)
Definition: epph.cpp:452
void Thomas(double *zMax, double *z0, double *Av, int nn)
Definition: sfa.cpp:152

SHOGUN Machine Learning Toolbox - Documentation