Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Sander Dieleman"'
Publikováno v:
Proceedings of the 24th International Conference on Intelligent User Interfaces.
We present Piano Genie, an intelligent controller which allows non-musicians to improvise on the piano. With Piano Genie, a user performs on a simple interface with eight buttons, and their performance is decoded into the space of plausible piano mus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90c81581a94e979bcba304317becbe79
https://doi.org/10.1145/3301275.3302288
https://doi.org/10.1145/3301275.3302288
Autor:
John Nham, David Silver, Ilya Sutskever, Demis Hassabis, George van den Driessche, Arthur Guez, Dominik Grewe, Marc Lanctot, Thore Graepel, Laurent Sifre, Chris J. Maddison, Nal Kalchbrenner, Ioannis Antonoglou, Timothy P. Lillicrap, Koray Kavukcuoglu, Julian Schrittwieser, Madeleine Leach, Aja Huang, Veda Panneershelvam, Sander Dieleman
Publikováno v:
Nature. 529:484-489
The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae3953e2190143a462dcebd18f7c4495
https://doi.org/10.1038/nature16961
https://doi.org/10.1038/nature16961
Autor:
Balázs Hidasi, Alexandros Karatzoglou, Oren Sar-Shalom, Bracha Shapira, Domonkos Tikk, Flavian Vasile, Sander Dieleman
Publikováno v:
Proceedings of the 12th ACM Conference on Recommender Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1bfc41b25c9b74cccd6555a0a0d02b69
https://doi.org/10.1145/3240323.3240333
https://doi.org/10.1145/3240323.3240333
Music generation has generally been focused on either creating scores or interpreting them. We discuss differences between these two problems and propose that, in fact, it may be valuable to work in the space of direct $\it performance$ generation: j
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dbf2099dae2aa08e10abd982b8f68cc3
Publikováno v:
Monthly Notices of the Royal Astronomical Society. 450:1441-1459
Measuring the morphological parameters of galaxies is a key requirement for studying their formation and evolution. Surveys such as the Sloan Digital Sky Survey (SDSS) have resulted in the availability of very large collections of images, which have
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a2f8e6ae61b95c37f943f634f2c5a479
https://doi.org/10.1093/mnras/stv632
https://doi.org/10.1093/mnras/stv632
Autor:
Flavian Vasile, Alexandros Karatzoglou, Bracha Shapira, Sander Dieleman, Balázs Hidasi, Domonkos Tikk, Oren Sar-Shalom
Publikováno v:
RecSys
Deep learning methods became widely popular in the recommender systems community in 2016, in part thanks to the previous event of the DLRS workshop series. Now, deep learning has been embedded in the main conference as well and initial research direc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5f25fe254aa2b87288e8d68acd61692
https://doi.org/10.1145/3109859.3109953
https://doi.org/10.1145/3109859.3109953
Autor:
Sander Dieleman
Publikováno v:
DLRS@RecSys
The advent of deep learning has made it possible to extract high-level information from perceptual signals without having to specify manually and explicitly how to obtain it; instead, this can be learned from examples. This creates opportunities for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db1fe7864265e316b331256ed66db5a6
https://doi.org/10.1145/2988450.2991128
https://doi.org/10.1145/2988450.2991128
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78f9e6b005abe716cc2acd4bae1584c8
http://arxiv.org/abs/1506.01911
http://arxiv.org/abs/1506.01911
Autor:
Benjamin Schrauwen, Sander Dieleman
Publikováno v:
ICASSP
Content-based music information retrieval tasks have traditionally been solved using engineered features and shallow processing architectures. In recent years, there has been increasing interest in using feature learning and deep architectures instea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4fe57d46420d20a7d6c3353832603bc0
https://doi.org/10.1109/icassp.2014.6854950
https://doi.org/10.1109/icassp.2014.6854950
Publikováno v:
IJCNN
IEEE International Joint Conference on Neural Networks (IJCNN)
IEEE International Joint Conference on Neural Networks (IJCNN)
In the field of Reservoir Computing, scaling the spectral radius of the weight matrix of a random recurrent neural network to below unity is a commonly used method to ensure the Echo State Property. Recently it has been shown that this condition is t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ba8505b7b8844134f84cebbd5082334
https://doi.org/10.1109/ijcnn.2013.6706899
https://doi.org/10.1109/ijcnn.2013.6706899