Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Ankur Mali"'
Autor:
Pengliang Yu, Ankur Mali, Thejasvi Velaga, Alex Bi, Jiayi Yu, Chris Marone, Parisa Shokouhi, Derek Elsworth
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-12 (2024)
Abstract We link changes in crustal permeability to informative features of microearthquakes (MEQs) using two field hydraulic stimulation experiments where both MEQs and permeability evolution are recorded simultaneously. The Bidirectional Long Short
Externí odkaz:
https://doaj.org/article/4f6d4a86a709439d8618fce86a5e36ff
Publikováno v:
Nature Communications, Vol 14, Iss 1, Pp 1-12 (2023)
Abstract Predicting failure in solids has broad applications including earthquake prediction which remains an unattainable goal. However, recent machine learning work shows that laboratory earthquakes can be predicted using micro-failure events and t
Externí odkaz:
https://doaj.org/article/790364c6ca064117b40719044b3a7f75
Publikováno v:
International Journal of Orthopaedics Sciences. 9:328-331
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9472dc9fdb39d290e694d780272130bb
https://doi.org/10.22271/ortho.2023.v9.i1e.3315
https://doi.org/10.22271/ortho.2023.v9.i1e.3315
Recent laboratory studies of fault friction have shown that deep learning can accurately predict the magnitude and timing of stick-slip sliding events, the laboratory equivalent of earthquakes, from the preceding acoustic emissions (AE) events or tim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa6a3e0a422e2a9cbdaa651fb4762135
https://doi.org/10.5194/egusphere-egu23-15437
https://doi.org/10.5194/egusphere-egu23-15437
Publikováno v:
International Journal of Orthopaedics Sciences. 7:42-45
Introduction: Osteoarthritis is thought to be the most prevalent chronic joint disease. Total knee arthroplasty is now s reliable treatment for severe arthritis and is commonly done for end stage arthritis of knee. The results of TKA are predictable
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9974cd7762787d01eca5607087c7380f
https://doi.org/10.22271/ortho.2021.v7.i3a.2726
https://doi.org/10.22271/ortho.2021.v7.i3a.2726
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:5006-5015
Automated mathematical reasoning is a challenging problem that requires an agent to learn algebraic patterns that contain long-range dependencies. Two particular tasks that test this type of reasoning are (1)mathematical equation verification,which r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1ed6fe7c4943676d9fb9b17a0123ab95
https://doi.org/10.1609/aaai.v35i6.16634
https://doi.org/10.1609/aaai.v35i6.16634
Publikováno v:
IEEE Transactions on Artificial Intelligence. 1:193-205
To learn complex formal grammars, recurrent neural networks (RNNs) require sufficient computational resources to ensure correct grammar recognition. One approach to expand model capacity is to couple an RNN to an external stack memory. Here, we intro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4fec0b23c86c253417f4aa2003e0375b
https://doi.org/10.1109/tai.2021.3055167
https://doi.org/10.1109/tai.2021.3055167
Recent advances in deep learning have led to superhuman performance across a variety of applications. Recently, these methods have been successfully employed to improve the rate-distortion performance in the task of image compression. However, curren
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::90246dc4f552379bfa6bf040ff2ae9c7
Autor:
Alexander G. Ororbia, Ankur Mali
Publikováno v:
AAAI
Finding biologically plausible alternatives to back-propagation of errors is a fundamentally important challenge in artificial neural network research. In this paper, we propose a learning algorithm called error-driven Local Representation Alignment
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::67cfeddd0c47e40abd0811d22ee62d12
https://doi.org/10.1609/aaai.v33i01.33014651
https://doi.org/10.1609/aaai.v33i01.33014651