Mercurial > hg > hybrid-music-recommender-using-content-based-and-social-information

annotate Report/references.bib @ 47:b0186d4a4496 tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Move 7Digital dataset to Downloads
author Paulo Chiliguano <p.e.chiliguano@se14.qmul.ac.uk>
date Sat, 09 Jul 2022 00:50:43 -0500
parents eba57dbe56f3
children
rev   line source
p@30 1 @incollection{bengio2012practical,
p@30 2 title={Practical recommendations for gradient-based training of deep architectures},
p@30 3 author={Bengio, Yoshua},
p@30 4 booktitle={Neural Networks: Tricks of the Trade},
p@30 5 pages={437--478},
p@30 6 year={2012},
p@30 7 publisher={Springer}
p@30 8 }
p@30 9
p@29 10 @article{scikit-learn,
p@29 11 title={Scikit-learn: Machine Learning in {P}ython},
p@29 12 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
p@29 13 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
p@29 14 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
p@29 15 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
p@29 16 journal={Journal of Machine Learning Research},
p@29 17 volume={12},
p@29 18 pages={2825--2830},
p@29 19 year={2011}
p@29 20 }
p@28 21 @inproceedings{gallagher2007bayesian,
p@28 22 title={Bayesian inference in estimation of distribution algorithms},
p@28 23 author={Gallagher, Marcus and Wood, Ian and Keith, Jonathan and Sofronov, George},
p@28 24 booktitle={Evolutionary Computation, 2007. CEC 2007. IEEE Congress on},
p@28 25 pages={127--133},
p@28 26 year={2007},
p@28 27 organization={IEEE}
p@28 28 }
p@28 29 @ARTICLE{Ding2015451,
p@28 30 author={Ding, C. and Ding, L. and Peng, W.},
p@28 31 title={Comparison of effects of different learning methods on estimation of distribution algorithms},
p@28 32 journal={Journal of Software Engineering},
p@28 33 year={2015},
p@28 34 volume={9},
p@28 35 number={3},
p@28 36 pages={451-468},
p@28 37 doi={10.3923/jse.2015.451.468},
p@29 38 note={},
p@28 39 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84924609049&partnerID=40&md5=e6419e97e218f8ef1600e3d21e6a9e36},
p@28 40 document_type={Article},
p@28 41 source={Scopus},
p@28 42 }
p@28 43
p@28 44 @ARTICLE{Jin2014113,
p@28 45 author={Jin, C. and Jin, S.-W.},
p@28 46 title={Software reliability prediction model based on support vector regression with improved estimation of distribution algorithms},
p@28 47 journal={Applied Soft Computing Journal},
p@28 48 year={2014},
p@28 49 volume={15},
p@28 50 pages={113-120},
p@28 51 doi={10.1016/j.asoc.2013.10.016},
p@29 52 note={},
p@28 53 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84889065631&partnerID=40&md5=6ba595eee679fa8355329646504b3ae3},
p@28 54 document_type={Article},
p@28 55 source={Scopus},
p@28 56 }
p@28 57 @online{1_ufldlstanfordedu_2015,
p@28 58 author={Ufldl.stanford.edu,},
p@28 59 title={Unsupervised Feature Learning and Deep Learning Tutorial},
p@28 60 url={http://ufldl.stanford.edu/tutorial/supervised/ConvolutionalNeuralNetwork/},
p@28 61 urldate={2015-8-30},
p@28 62 year={2015}
p@28 63 }
p@27 64 @online{1_lecun_2015,
p@27 65 author={LeCun, Yann},
p@27 66 title={MNIST Demos on Yann LeCun's website},
p@27 67 url={http://yann.lecun.com/exdb/lenet/},
p@27 68 urldate={2015-8-30},
p@27 69 journal={Yann.lecun.com},
p@27 70 year={2015}
p@27 71 }
p@27 72 @online{1_brown_2014,
p@27 73 author={Brown, Larry},
p@27 74 title={Accelerate Machine Learning with the cuDNN Deep Neural Network Library},
p@27 75 url={http://devblogs.nvidia.com/parallelforall/accelerate-machine-learning-cudnn-deep-neural-network-library/},
p@27 76 urldate={2015-8-30},
p@27 77 journal={Parallel Forall},
p@27 78 year={2014}
p@27 79 }
p@27 80
p@27 81 @article{hinton2012deep,
p@27 82 title={Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups},
p@27 83 author={Hinton, Geoffrey and Deng, Li and Yu, Dong and Dahl, George E and Mohamed, Abdel-rahman and Jaitly, Navdeep and Senior, Andrew and Vanhoucke, Vincent and Nguyen, Patrick and Sainath, Tara N and others},
p@27 84 journal={Signal Processing Magazine, IEEE},
p@27 85 volume={29},
p@27 86 number={6},
p@27 87 pages={82--97},
p@27 88 year={2012},
p@27 89 publisher={IEEE}
p@27 90 }
p@27 91 @article{weston2012latent,
p@27 92 title={Latent collaborative retrieval},
p@27 93 author={Weston, Jason and Wang, Chong and Weiss, Ron and Berenzweig, Adam},
p@27 94 journal={arXiv preprint arXiv:1206.4603},
p@27 95 year={2012}
p@27 96 }
p@27 97
p@27 98 @MISC{Bastien-Theano-2012,
p@27 99 author = {Bastien, Fr{\'{e}}d{\'{e}}ric and Lamblin, Pascal and Pascanu, Razvan and Bergstra, James and Goodfellow, Ian J. and Bergeron, Arnaud and Bouchard, Nicolas and Bengio, Yoshua},
p@27 100 title = {Theano: new features and speed improvements},
p@27 101 year = {2012},
p@27 102 howpublished = {Deep Learning and Unsupervised Feature Learning NIPS 2012 Workshop},
p@27 103 abstract = {Theano is a linear algebra compiler that optimizes a user’s symbolically-specified
p@27 104 mathematical computations to produce efficient low-level implementations. In
p@27 105 this paper, we present new features and efficiency improvements to Theano, and
p@27 106 benchmarks demonstrating Theano’s performance relative to Torch7, a recently
p@27 107 introduced machine learning library, and to RNNLM, a C++ library targeted at
p@27 108 recurrent neural networks.}
p@27 109 }
p@27 110
p@27 111 @INPROCEEDINGS{bergstra+al:2010-scipy,
p@27 112 author = {Bergstra, James and Breuleux, Olivier and Bastien, Fr{\'{e}}d{\'{e}}ric and Lamblin, Pascal and Pascanu, Razvan and Desjardins, Guillaume and Turian, Joseph and Warde-Farley, David and Bengio, Yoshua},
p@27 113 month = jun,
p@27 114 title = {Theano: a {CPU} and {GPU} Math Expression Compiler},
p@27 115 booktitle = {Proceedings of the Python for Scientific Computing Conference ({SciPy})},
p@27 116 year = {2010},
p@27 117 location = {Austin, TX},
p@27 118 note = {Oral Presentation},
p@27 119 abstract = {Theano is a compiler for mathematical expressions in Python that combines the convenience of NumPy’s syntax with the speed of optimized native machine language. The user composes mathematical expressions in a high-level description that mimics NumPy’s syntax and semantics, while being statically typed and
p@27 120 functional (as opposed to imperative). These expressions allow Theano to provide symbolic differentiation. Before performing computation, Theano optimizes the choice of expressions, translates
p@27 121 them into C++ (or CUDA for GPU), compiles them into dynamically loaded Python modules, all automatically. Common machine learning algorithms implemented with Theano are from 1.6× to 7.5× faster than competitive alternatives (including those implemented with C/C++, NumPy/SciPy and MATLAB) when compiled for the
p@27 122 CPU and between 6.5× and 44× faster when compiled for the GPU. This paper illustrates how to use Theano, outlines the scope of the compiler, provides benchmarks on both CPU and GPU processors, and explains its overall design.}
p@27 123 }
p@27 124
p@27 125 @article{kereliuk15,
p@27 126 title={Deep Learning and Music Adversaries},
p@27 127 author={Kereliuk, Corey and Sturm, Bob L and Larsen, Jan},
p@27 128 journal={arXiv preprint arXiv:1507.04761},
p@27 129 year={2015}
p@27 130 }
p@27 131
p@27 132 @article{DBLP:journals/corr/abs-1305-1114,
p@27 133 author = {Djallel Bouneffouf},
p@27 134 title = {Towards User Profile Modelling in Recommender System},
p@27 135 journal = {CoRR},
p@27 136 volume = {abs/1305.1114},
p@27 137 year = {2013},
p@27 138 url = {http://arxiv.org/abs/1305.1114},
p@27 139 timestamp = {Sun, 02 Jun 2013 20:48:21 +0200},
p@27 140 biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/abs-1305-1114},
p@27 141 bibsource = {dblp computer science bibliography, http://dblp.org}
p@27 142 }
p@27 143
p@27 144 @ARTICLE{Yao2015453,
p@27 145 author={Yao, L. and Sheng, Q.Z. and Ngu, A.H.H. and Yu, J. and Segev, A.},
p@27 146 title={Unified collaborative and content-based web service recommendation},
p@27 147 journal={IEEE Transactions on Services Computing},
p@27 148 year={2015},
p@27 149 volume={8},
p@27 150 number={3},
p@27 151 pages={453-466},
p@27 152 doi={10.1109/TSC.2014.2355842},
p@27 153 art_number={6894179},
p@27 154 note={},
p@27 155 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84932619562&partnerID=40&md5=4483a697e12fc53f620393586f85aebe},
p@27 156 document_type={Article},
p@27 157 source={Scopus},
p@27 158 }
p@27 159 @online{1_blogseagatesoftcom_2015,
p@27 160 author={Blog.seagatesoft.com,},
p@27 161 title={Belajar Sistem Perekomendasi « Corat-coret di Halaman Web},
p@27 162 url={http://blog.seagatesoft.com/2013/07/14/belajar-sistem-perekomendasi/},
p@27 163 urldate={2015-8-29},
p@27 164 year={2015}
p@27 165 }
p@27 166
p@27 167 @inproceedings{sarwar2001item,
p@27 168 title={Item-based collaborative filtering recommendation algorithms},
p@27 169 author={Sarwar, Badrul and Karypis, George and Konstan, Joseph and Riedl, John},
p@27 170 booktitle={Proceedings of the 10th international conference on World Wide Web},
p@27 171 pages={285--295},
p@27 172 year={2001},
p@27 173 organization={ACM}
p@27 174 }
p@27 175
p@27 176 @CONFERENCE{Hu2008263,
p@27 177 author={Hu, Y. and Volinsky, C. and Koren, Y.},
p@27 178 title={Collaborative filtering for implicit feedback datasets},
p@27 179 journal={Proceedings - IEEE International Conference on Data Mining, ICDM},
p@27 180 year={2008},
p@27 181 pages={263-272},
p@27 182 doi={10.1109/ICDM.2008.22},
p@27 183 art_number={4781121},
p@27 184 note={},
p@27 185 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-67049164166&partnerID=40&md5=01238b08208962fd0fdcc7503fa3af99},
p@27 186 document_type={Conference Paper},
p@27 187 source={Scopus},
p@27 188 }
p@27 189
p@27 190 @online{2_the_economist_2005,
p@27 191 author={The Economist,},
p@27 192 title={United we find},
p@27 193 url={http://www.economist.com/node/3714044},
p@27 194 urldate={2015-8-28},
p@27 195 year={2005}
p@27 196 }
p@27 197
p@27 198 @online{1_siddharths_blog_2013,
p@27 199 author={},
p@27 200 title={Recommendation Engine},
p@27 201 url={https://spatnaik77.wordpress.com/2013/07/17/recommendation-engine/},
p@27 202 urldate={2015-8-28},
p@27 203 year={2013}
p@27 204 }
p@27 205
p@27 206 @online{1_deeplearning.net_2015,
p@27 207 author={Deeplearning.net,},
p@27 208 title={Convolutional Neural Networks (LeNet) — DeepLearning 0.1 documentation},
p@27 209 url={http://deeplearning.net/tutorial/lenet.html},
p@27 210 urldate={2015-8-28},
p@27 211 year={2015}
p@27 212 }
p@27 213 @ARTICLE{Casey2008668,
p@27 214 author={Casey, M.A. and Veltkamp, R. and Goto, M. and Leman, M. and Rhodes, C. and Slaney, M.},
p@27 215 title={Content-based music information retrieval: Current directions and future challenges},
p@27 216 journal={Proceedings of the IEEE},
p@27 217 year={2008},
p@27 218 volume={96},
p@27 219 number={4},
p@27 220 pages={668-696},
p@27 221 doi={10.1109/JPROC.2008.916370},
p@27 222 art_number={4472077},
p@27 223 note={},
p@27 224 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-64649105397&partnerID=40&md5=2d8ec7231e10bc686566dd419ce47ae8},
p@27 225 document_type={Article},
p@27 226 source={Scopus},
p@27 227 }
p@27 228
p@27 229 @CONFERENCE{Celma2006,
p@27 230 author={Celma, O. and Herrera, P. and Serra, X.},
p@27 231 title={Bridging the music semantic gap},
p@27 232 journal={CEUR Workshop Proceedings},
p@27 233 year={2006},
p@27 234 volume={187},
p@27 235 page_count={12},
p@27 236 note={},
p@27 237 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84884332226&partnerID=40&md5=d028cb2aca5d2d6d8f25a8a8b555edbf},
p@27 238 document_type={Conference Paper},
p@27 239 source={Scopus},
p@27 240 }
p@27 241
p@27 242 @online{1_spotify_press_2014,
p@27 243 author={},
p@27 244 title={Spotify Acquires The Echo Nest},
p@27 245 url={https://press.spotify.com/us/2014/03/06/spotify-acquires-the-echo-nest/},
p@27 246 urldate={2015-8-27},
p@27 247 year={2014}
p@27 248 }
p@27 249 @article{smith2009social,
p@27 250 title={The social media revolution},
p@27 251 author={Smith, Tom},
p@27 252 journal={International journal of market research},
p@27 253 volume={51},
p@27 254 number={4},
p@27 255 pages={559--561},
p@27 256 year={2009}
p@27 257 }
p@27 258 @article{Putzke2014519,
p@27 259 title = "Cross-cultural gender differences in the adoption and usage of social media platforms – An exploratory study of Last.FM ",
p@27 260 journal = "Computer Networks ",
p@27 261 volume = "75, Part B",
p@27 262 number = "",
p@27 263 pages = "519 - 530",
p@27 264 year = "2014",
p@27 265 note = "Special Issue on Online Social NetworksThe Connectedness, Pervasiveness and Ubiquity of Online Social Networks ",
p@27 266 issn = "1389-1286",
p@27 267 doi = "http://dx.doi.org/10.1016/j.comnet.2014.08.027",
p@27 268 url = "http://www.sciencedirect.com/science/article/pii/S1389128614003302",
p@27 269 author = "Johannes Putzke and Kai Fischbach and Detlef Schoder and Peter A. Gloor",
p@27 270 keywords = "Adoption",
p@27 271 keywords = "Cross-cultural differences",
p@27 272 keywords = "Gender",
p@27 273 keywords = "Social media ",
p@27 274 abstract = "Abstract This paper examines cross-cultural gender differences in the adoption and usage of the social media platform Last.FM. From a large-scale empirical study of 3748 Last.FM users from Australia, Finland, Germany, and the United States of America, we find: (1) men listen to more pieces of music on social media platforms than do women; (2) women focus their listening on fewer musical genres and fewer tracks than do men; (3) women register on Last.FM later than do “early adopting” men (absolutely and in comparison to their friends), but at a younger age; (4) women maintain more virtual friendships on Last.FM than do men; and (5) women, when choosing music to listen to on social media platforms, are more likely than are men to choose tracks that correspond to mainstream tastes. "
p@27 275 }
p@27 276
p@27 277 @CONFERENCE{Park200811,
p@27 278 author={Park, Y.-J. and Tuzhilin, A.},
p@27 279 title={The long tail of recommender systems and how to leverage it},
p@27 280 journal={RecSys'08: Proceedings of the 2008 ACM Conference on Recommender Systems},
p@27 281 year={2008},
p@27 282 pages={11-18},
p@27 283 doi={10.1145/1454008.1454012},
p@27 284 note={},
p@27 285 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-63449136183&partnerID=40&md5=648e50cac2d99764f891b5bc4b97bbfe},
p@27 286 document_type={Conference Paper},
p@27 287 source={Scopus},
p@27 288 }
p@27 289 @CONFERENCE{Dai20141760,
p@27 290 author={Dai, C. and Qian, F. and Jiang, W. and Wang, Z. and Wu, Z.},
p@27 291 title={A personalized recommendation system for netease dating site},
p@27 292 journal={Proceedings of the VLDB Endowment},
p@27 293 year={2014},
p@27 294 volume={7},
p@27 295 number={13},
p@27 296 pages={1760-1765},
p@27 297 note={},
p@27 298 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84905828317&partnerID=40&md5=90fbd8b20ad39757895bdee3ca58f459},
p@27 299 document_type={Article},
p@27 300 source={Scopus},
p@27 301 }
p@27 302
p@27 303 @CONFERENCE{Yin2012896,
p@27 304 author={Yin, H. and Cui, B. and Li, J. and Yao, J. and Chen, C.},
p@27 305 title={Challenging the long tail recommendation},
p@27 306 journal={Proceedings of the VLDB Endowment},
p@27 307 year={2012},
p@27 308 volume={5},
p@27 309 number={9},
p@27 310 pages={896-907},
p@27 311 note={},
p@27 312 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84863735354&partnerID=40&md5=2bd887772ba832fbbb4631afd25514d9},
p@27 313 document_type={Article},
p@27 314 source={Scopus},
p@27 315 }
p@27 316
p@27 317 @online{1_hypebot.com_2015,
p@27 318 author={Hypebot.com,},
p@27 319 title={Streaming Music Discovery: It's More Than Just Showing Album Credits - hypebot},
p@27 320 url={http://www.hypebot.com/hypebot/2015/07/streaming-music-discovery-its-more-than-just-showing-album-credits.html},
p@27 321 urldate={2015-8-26},
p@27 322 year={2015}
p@27 323 }
p@27 324
p@27 325 @online{ringen_2015,
p@27 326 author={Ringen, Jonathan},
p@27 327 title={Spotify, Apple Music, And The Streaming Wars: 5 Things We've Learned},
p@27 328 url={http://www.fastcompany.com/3048653/innovation-agents/listen-up},
p@27 329 urldate={2015-8-26},
p@27 330 journal={Fast Company},
p@27 331 year={2015}
p@27 332 }
p@27 333
p@27 334 @online{recsys2012,
p@27 335 author = {},
p@27 336 title = {Recommender Systems},
p@27 337 year = {2012},
p@27 338 url = {http://recommender-systems.org/},
p@27 339 note = {[Accessed: 26th August 2015]}
p@27 340 }
p@27 341
p@26 342 @article{Hejazi15,
p@26 343 author={Hejazi,S. A. and Stapleton,S. P.},
p@26 344 year={2015},
p@26 345 title={A self-organized network for load balancing using intelligent distributed antenna system},
p@26 346 journal={Canadian Journal of Electrical and Computer Engineering},
p@26 347 volume={38},
p@26 348 number={2},
p@26 349 pages={89-99},
p@26 350 url={www.scopus.com},
p@26 351 }
p@27 352
p@26 353
p@26 354 @book{larranaga2002estimation,
p@26 355 title={Estimation of distribution algorithms: A new tool for evolutionary computation},
p@26 356 author={Larranaga, Pedro and Lozano, Jose A},
p@26 357 volume={2},
p@26 358 year={2002},
p@26 359 publisher={Springer Science \& Business Media}
p@26 360 }
p@26 361
p@26 362 @incollection{melville2010recommender,
p@26 363 title={Recommender systems},
p@26 364 author={Melville, Prem and Sindhwani, Vikas},
p@26 365 booktitle={Encyclopedia of machine learning},
p@26 366 pages={829--838},
p@26 367 year={2010},
p@26 368 publisher={Springer}
p@26 369 }
p@26 370
p@20 371 @incollection{Lops2011,
p@20 372 year={2011},
p@20 373 isbn={978-0-387-85819-7},
p@20 374 booktitle={Recommender Systems Handbook},
p@20 375 editor={Ricci, Francesco and Rokach, Lior and Shapira, Bracha and Kantor, Paul B.},
p@20 376 doi={10.1007/978-0-387-85820-3_3},
p@20 377 title={Content-based Recommender Systems: State of the Art and Trends},
p@27 378 url={http://dx.doi.org/10.1007/978-0-387-85820-3_3},
p@20 379 publisher={Springer US},
p@20 380 author={Lops, Pasquale and de Gemmis, Marco and Semeraro, Giovanni},
p@20 381 pages={73-105},
p@20 382 language={English}
p@20 383 }
p@20 384
p@20 385 @ARTICLE{Burke2002331,
p@20 386 author={Burke, R.},
p@20 387 title={Hybrid recommender systems: Survey and experiments},
p@20 388 journal={User Modelling and User-Adapted Interaction},
p@20 389 year={2002},
p@20 390 volume={12},
p@20 391 number={4},
p@20 392 pages={331-370},
p@20 393 doi={10.1023/A:1021240730564},
p@27 394 note={},
p@27 395 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-0036959356&partnerID=40&md5=28885a102109be826507abc2435117a7},
p@20 396 document_type={Article},
p@20 397 source={Scopus},
p@20 398 }
p@20 399
p@20 400 @ARTICLE{Yoshii2008435,
p@20 401 author={Yoshii, K. and Goto, M. and Komatani, K. and Ogata, T. and Okuno, H.G.},
p@20 402 title={An efficient hybrid music recommender system using an incrementally trainable probabilistic generative model},
p@20 403 journal={IEEE Transactions on Audio, Speech and Language Processing},
p@20 404 year={2008},
p@20 405 volume={16},
p@20 406 number={2},
p@20 407 pages={435-447},
p@20 408 doi={10.1109/TASL.2007.911503},
p@20 409 art_number={4432655},
p@27 410 note={},
p@27 411 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-39649112098&partnerID=40&md5=6827f82844ae1da58a6fa95caf5092d9},
p@20 412 document_type={Article},
p@20 413 source={Scopus},
p@20 414 }
p@20 415
p@20 416
p@20 417 @article{JCC4:JCC4393,
p@20 418 author = {boyd, danah m. and Ellison, Nicole B.},
p@20 419 title = {Social Network Sites: Definition, History, and Scholarship},
p@20 420 journal = {Journal of Computer-Mediated Communication},
p@20 421 volume = {13},
p@20 422 number = {1},
p@20 423 publisher = {Blackwell Publishing Inc},
p@20 424 issn = {1083-6101},
p@20 425 url = {http://dx.doi.org/10.1111/j.1083-6101.2007.00393.x},
p@20 426 doi = {10.1111/j.1083-6101.2007.00393.x},
p@20 427 pages = {210--230},
p@20 428 year = {2007},
p@20 429 }
p@20 430
p@20 431 @ARTICLE{Castanedo2013,
p@20 432 author={Castanedo, F.},
p@20 433 title={A review of data fusion techniques},
p@20 434 journal={The Scientific World Journal},
p@20 435 year={2013},
p@20 436 volume={2013},
p@20 437 doi={10.1155/2013/704504},
p@20 438 art_number={704504},
p@27 439 note={},
p@27 440 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84888882639&partnerID=40&md5=827fabc750db24f662fdae1c798f2507},
p@20 441 document_type={Review},
p@20 442 source={Scopus},
p@20 443 }
p@20 444
p@20 445
p@20 446 @CONFERENCE{Lee20091096,
p@20 447 author={Lee, H. and Yan, L. and Pham, P. and Ng, A.Y.},
p@20 448 title={Unsupervised feature learning for audio classification using convolutional deep belief networks},
p@20 449 journal={Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference},
p@20 450 year={2009},
p@20 451 pages={1096-1104},
p@27 452 note={},
p@27 453 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84863380535&partnerID=40&md5=e872a6227c816850167f91bb2d41d8b7},
p@20 454 document_type={Conference Paper},
p@20 455 source={Scopus},
p@20 456 }
p@20 457
p@20 458
p@20 459 @TechReport {export:115396,
p@20 460 abstract = {<p>Recommender systems are now popular both commercially and in the research
p@20 461 community, where many approaches have been suggested for providing
p@20 462 recommendations. In many cases a system designer that wishes to employ a
p@20 463 recommendation system must choose between a set of candidate approaches. A first
p@20 464 step towards selecting an appropriate algorithm is to decide which properties of
p@20 465 the application to focus upon when making this choice. Indeed, recommendation
p@20 466 systems have a variety of properties that may affect user experience, such as
p@20 467 accuracy, robustness, scalability, and so forth. In this paper we discuss how to
p@20 468 compare recommenders based on a set of properties that are relevant for e
p@20 469 application. We focus on comparative studies, where a few algorithms are compared
p@20 470 using some evaluation metric, rather than absolute benchmarking of algorithms. We
p@20 471 describe experimental settings appropriate for making choices between algorithms.
p@20 472 We review three types of experiments, starting with an offline setting, where
p@20 473 recommendation approaches are compared without user interaction, then reviewing
p@20 474 user studies, where a small group of subjects experiment with the system and
p@20 475 report on the experience, and finally describe large scale online experiments,
p@20 476 where real user populations interact with the system. In each of these cases we
p@20 477 describe types of questions that can be answered, and suggest protocols for
p@20 478 experimentation. We also discuss how to draw trustworthy conclusions from e
p@20 479 conducted experiments. We then review a large set of properties, and explain how
p@20 480 to evaluate systems given relevant properties. We also survey a large set of
p@20 481 evaluation metrics in the context of the property that they evaluate.</p>},
p@20 482 author = {Guy Shani and Asela Gunawardana},
p@20 483 month = {November},
p@20 484 number = {MSR-TR-2009-159},
p@20 485 publisher = {Microsoft Research},
p@20 486 title = {Evaluating Recommender Systems},
p@20 487 url = {http://research.microsoft.com/apps/pubs/default.aspx?id=115396},
p@20 488 year = {2009},
p@20 489 }
p@20 490
p@20 491 @phdthesis {1242,
p@20 492 title = {Music Recommendation and Discovery in the Long Tail},
p@20 493 year = {2008},
p@20 494 school = {Universitat Pompeu Fabra},
p@20 495 address = {Barcelona},
p@20 496 abstract = {<p class="small">
p@20 497 Music consumption is biased towards a few popular artists. For instance, in 2007 only 1\% of
p@20 498 all digital tracks accounted for 80\% of all sales. Similarly, 1,000 albums accounted for 50\%
p@20 499 of all album sales, and 80\% of all albums sold were purchased less than 100 times. There is
p@20 500 a need to assist people to filter, discover, personalise and recommend from the huge amount
p@20 501 of music content available along the Long Tail.
p@20 502 </p>
p@20 503 <p class="small">
p@20 504 Current music recommendation algorithms try to
p@20 505 accurately predict what people demand to listen to. However, quite
p@20 506 often these algorithms tend to recommend popular -or well-known to the
p@20 507 user- music, decreasing the effectiveness of the recommendations. These
p@20 508 approaches focus on improving the accuracy of the recommendations. That
p@20 509 is, try to make
p@20 510 accurate predictions about what a user could listen to, or buy next,
p@20 511 independently of how
p@20 512 useful to the user could be the provided recommendations.
p@20 513 </p>
p@20 514 <p class="small">
p@20 515 In this Thesis we stress the importance of the user{\textquoteright}s
p@20 516 perceived quality of the recommendations. We model the Long Tail curve
p@20 517 of artist popularity to predict -potentially-
p@20 518 interesting and unknown music, hidden in the tail of the popularity
p@20 519 curve. Effective recommendation systems should promote novel and
p@20 520 relevant material (non-obvious recommendations), taken primarily from
p@20 521 the tail of a popularity distribution.
p@20 522 </p>
p@20 523 <p class="small">
p@20 524 The main contributions of this Thesis are: <em>(i)</em> a novel network-based approach for
p@20 525 recommender systems, based on the analysis of the item (or user) similarity graph, and the
p@20 526 popularity of the items, <em>(ii)</em> a user-centric evaluation that measures the user{\textquoteright}s relevance
p@20 527 and novelty of the recommendations, and <em>(iii)</em> two prototype systems that implement the
p@20 528 ideas derived from the theoretical work. Our findings have significant implications for
p@20 529 recommender systems that assist users to explore the Long Tail, digging for content they
p@20 530 might like.
p@20 531 </p>
p@20 532 },
p@27 533 url = {http://mtg.upf.edu/static/media/PhD_ocelma.pdf},
p@27 534 author = {Celma, \`{O}.}
p@20 535 }
p@21 536
p@21 537 @inproceedings{pachet2001musical,
p@21 538 title={Musical data mining for electronic music distribution},
p@21 539 author={Pachet, Fran{\c{c}}ois and Westermann, Gert and Laigre, Damien},
p@21 540 booktitle={Web Delivering of Music, 2001. Proceedings. First International Conference on},
p@21 541 pages={101--106},
p@21 542 year={2001},
p@21 543 organization={IEEE}
p@21 544 }
p@21 545
p@21 546 @ARTICLE{Tzanetakis2002293,
p@21 547 author={Tzanetakis, G. and Cook, P.},
p@21 548 title={Musical genre classification of audio signals},
p@21 549 journal={IEEE Transactions on Speech and Audio Processing},
p@21 550 year={2002},
p@21 551 volume={10},
p@21 552 number={5},
p@21 553 pages={293-302},
p@21 554 doi={10.1109/TSA.2002.800560},
p@27 555 note={},
p@27 556 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-0036648502&partnerID=40&md5=72d2fee186b42c9998f13415cbb79eea},
p@21 557 document_type={Article},
p@21 558 source={Scopus},
p@21 559 }
p@21 560
p@21 561 @CONFERENCE{Sturm20127,
p@21 562 author={Sturm, B.L.},
p@21 563 title={An analysis of the GTZAN music genre dataset},
p@21 564 journal={MIRUM 2012 - Proceedings of the 2nd International ACM Workshop on Music Information Retrieval with User-Centered and Multimodal Strategies, Co-located with ACM Multimedia 2012},
p@21 565 year={2012},
p@21 566 pages={7-12},
p@21 567 doi={10.1145/2390848.2390851},
p@27 568 note={},
p@27 569 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84870497334&partnerID=40&md5=40a48c1c9d787308dd315694b54b64ec},
p@21 570 document_type={Conference Paper},
p@21 571 source={Scopus},
p@21 572 }
p@21 573
p@21 574 @unpublished{Bengio-et-al-2015-Book,
p@21 575 title={Deep Learning},
p@21 576 author={Yoshua Bengio and Ian J. Goodfellow and Aaron Courville},
p@21 577 note={Book in preparation for MIT Press},
p@21 578 url={http://www.iro.umontreal.ca/~bengioy/dlbook},
p@21 579 year={2015}
p@21 580 }
p@21 581
p@21 582 @CONFERENCE{Sigtia20146959,
p@21 583 author={Sigtia, S. and Dixon, S.},
p@21 584 title={Improved music feature learning with deep neural networks},
p@21 585 journal={ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings},
p@21 586 year={2014},
p@21 587 pages={6959-6963},
p@21 588 doi={10.1109/ICASSP.2014.6854949},
p@21 589 art_number={6854949},
p@27 590 note={},
p@27 591 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84905259152&partnerID=40&md5=3441dfa8c7998a8eb39f668d43efb8a1},
p@21 592 document_type={Conference Paper},
p@21 593 source={Scopus},
p@21 594 }
p@21 595
p@21 596 @incollection{NIPS2013_5004,
p@21 597 title = {Deep content-based music recommendation},
p@21 598 author = {van den Oord, Aaron and Dieleman, Sander and Schrauwen, Benjamin},
p@21 599 booktitle = {Advances in Neural Information Processing Systems 26},
p@21 600 editor = {C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger},
p@21 601 pages = {2643--2651},
p@21 602 year = {2013},
p@21 603 publisher = {Curran Associates, Inc.},
p@21 604 url = {http://papers.nips.cc/paper/5004-deep-content-based-music-recommendation.pdf}
p@21 605 }
p@21 606
p@21 607 @incollection{pelikan2015estimation,
p@21 608 title={Estimation of Distribution Algorithms},
p@21 609 author={Pelikan, Martin and Hauschild, Mark W and Lobo, Fernando G},
p@21 610 booktitle={Springer Handbook of Computational Intelligence},
p@21 611 pages={899--928},
p@21 612 year={2015},
p@21 613 publisher={Springer}
p@21 614 }
p@21 615
p@21 616 @article{Santana:Bielza:Larrañaga:Lozano:Echegoyen:Mendiburu:Armañanzas:Shakya:2009:JSSOBK:v35i07,
p@21 617 author = "Roberto Santana and Concha Bielza and Pedro Larrañaga and Jose A. Lozano and Carlos Echegoyen and Alexander Mendiburu and Rubén Armañanzas and Siddartha Shakya",
p@21 618 title = "Mateda-2.0: A MATLAB Package for the Implementation and Analysis of Estimation of Distribution Algorithms",
p@21 619 journal = "Journal of Statistical Software",
p@21 620 volume = "35",
p@21 621 number = "7",
p@21 622 pages = "1--30",
p@21 623 day = "26",
p@21 624 month = "7",
p@21 625 year = "2010",
p@21 626 CODEN = "JSSOBK",
p@21 627 ISSN = "1548-7660",
p@21 628 bibdate = "2009-12-17",
p@21 629 URL = "http://www.jstatsoft.org/v35/i07",
p@21 630 accepted = "2009-12-17",
p@21 631 acknowledgement = "",
p@21 632 keywords = "",
p@21 633 submitted = "2009-04-15",
p@21 634 }
p@21 635
p@21 636 @ARTICLE{Liang2014781,
p@21 637 author={Liang, T. and Liang, Y. and Fan, J. and Zhao, J.},
p@21 638 title={A hybrid recommendation model based on estimation of distribution algorithms},
p@21 639 journal={Journal of Computational Information Systems},
p@21 640 year={2014},
p@21 641 volume={10},
p@21 642 number={2},
p@21 643 pages={781-788},
p@21 644 doi={10.12733/jcis9623},
p@27 645 note={},
p@27 646 url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84892865461&partnerID=40&md5=a2927d36b493e8ef4d1cdab3055fa68b},
p@21 647 document_type={Article},
p@21 648 source={Scopus},
p@21 649 }
p@21 650
p@21 651 @INPROCEEDINGS{Bertin-Mahieux2011,
p@21 652 author = {Thierry Bertin-Mahieux and Daniel P.W. Ellis and Brian Whitman and Paul Lamere},
p@21 653 title = {The Million Song Dataset},
p@21 654 booktitle = {{Proceedings of the 12th International Conference on Music Information
p@21 655 Retrieval ({ISMIR} 2011)}},
p@21 656 year = {2011},
p@21 657 owner = {thierry},
p@21 658 timestamp = {2010.03.07}
p@21 659 }
p@21 660
p@21 661 @inproceedings{zhang2014deep,
p@21 662 title={A deep representation for invariance and music classification},
p@21 663 author={Zhang, Chiyuan and Evangelopoulos, Georgios and Voinea, Stephen and Rosasco, Lorenzo and Poggio, Tomaso},
p@21 664 booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on},
p@21 665 pages={6984--6988},
p@21 666 year={2014},
p@21 667 organization={IEEE}
p@21 668 }