Zobrazeno 1 - 10
of 14
pro vyhledávání: '"David Duvenaud"'
Autor:
Rafael Gómez-Bombarelli, Jennifer N. Wei, David Duvenaud, José Miguel Hernández-Lobato, Benjamín Sánchez-Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D. Hirzel, Ryan P. Adams, Alán Aspuru-Guzik
Publikováno v:
ACS Central Science, Vol 4, Iss 2, Pp 268-276 (2018)
Externí odkaz:
https://doaj.org/article/b50d04155c7540d9bb8184b3e18b7d8a
Publikováno v:
ACS Central Science, Vol 2, Iss 10, Pp 725-732 (2016)
Externí odkaz:
https://doaj.org/article/bebf6f4e4fa24253a392c87141a52c66
Publikováno v:
Computer Graphics Forum. 38:379-391
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f8ace5aaf47fbaaf5b5ccafc187b910
https://doi.org/10.1111/cgf.13645
https://doi.org/10.1111/cgf.13645
Autor:
Alexey Radul, Daniel D. Johnson, Dimitrios Vytiniotis, Adam Paszke, Matthew J. Johnson, Jonathan Ragan-Kelley, Dougal Maclaurin, David Duvenaud
We present a novel programming language design that attempts to combine the clarity and safety of high-level functional languages with the efficiency and parallelism of low-level numerical languages. We treat arrays as eagerly-memoized functions on t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bee088062310adb84ba166d2b5685746
Publikováno v:
ACL (1)
Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes. However, methods for measuring and removing such biases remain poorly understood. We show that for any embedding model that implicitly does m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c96e735e23a57e27ee6c667bdcb8684
https://doi.org/10.18653/v1/p19-1166
https://doi.org/10.18653/v1/p19-1166
Publikováno v:
ACL (1)
A surprising property of word vectors is that word analogies can often be solved with vector arithmetic. However, it is unclear why arithmetic operators correspond to non-linear embedding models such as skip-gram with negative sampling (SGNS). We pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4a5d8fc42bed02c3068cfe81cee0593
https://doi.org/10.18653/v1/p19-1315
https://doi.org/10.18653/v1/p19-1315
Publikováno v:
ACS Central Science, Vol 2, Iss 10, Pp 725-732 (2016)
ACS Central Science
ACS Central Science
Reaction prediction remains one of the major challenges for organic chemistry, and is a pre-requisite for efficient synthetic planning. It is desirable to develop algorithms that, like humans, "learn" from being exposed to examples of the application
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cfaaaa82d349785d8f38e2a0f5cc6d98
https://doaj.org/article/bebf6f4e4fa24253a392c87141a52c66
https://doaj.org/article/bebf6f4e4fa24253a392c87141a52c66
MotivationDetermining RNA binding protein(RBP) binding specificity is crucial for understanding many cellular processes and genetic disorders. RBP binding is known to be affected by both the sequence and structure of RNAs. Deep learning can be used t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ae296e78bad234e342eea8724809307
Publikováno v:
bioRxiv
Cognitive Neuroscience
Cognitive Neuroscience
How do people recognize and learn about complex functional structure? Taking inspiration from other areas of cognitive science, we propose that this is achieved by harnessing compositionality: complex structure is decomposed into simpler building blo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::725ac6eba4b61e7f601406023d4e1336
https://hdl.handle.net/1721.1/133410
https://hdl.handle.net/1721.1/133410
Publikováno v:
IUI
Novice composers often find it difficult to go beyond common chord progressions. To make it easier for composers to experiment with radical chord choices, we built a creativity support tool, ChordRipple, which makes chord recommendations that aim to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c08c084360f38de633e141ab5efc6a9
https://doi.org/10.1145/2856767.2856792
https://doi.org/10.1145/2856767.2856792