Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Arjun Manoharan"'
Publikováno v:
Digital Presentation and Preservation of Cultural and Scientific Heritage, Vol 10 (2020)
The paper sets to define a comparison of emotions across 3 different cultures namely Canadian French, Italian, and North American. This was achieved using speech samples for each of the three languages subject to our study. The features used were MFC
Externí odkaz:
https://doaj.org/article/e347a63f15984e988b26a85d260bf508
Publikováno v:
Proceedings of the International Conference on Automated Planning and Scheduling. 31:533-541
State abstraction is necessary for better task transfer in complex reinforcement learning environments. Inspired by the benefit of state abstraction in MAXQ and building upon hybrid planner-RL architectures, we propose RePReL, a hierarchical framewor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed7882990f8420c3bce61acf721d5686
https://doi.org/10.1609/icaps.v31i1.16001
https://doi.org/10.1609/icaps.v31i1.16001
Publikováno v:
Large-Scale Scientific Computing ISBN: 9783030975487
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::47830187abd549801809e259d05a2568
https://doi.org/10.1007/978-3-030-97549-4_52
https://doi.org/10.1007/978-3-030-97549-4_52
Autor:
Shikha Bordia, Pawan Sasanka Ammanamanchi, Maneesh Singh, Ramakanth Pasunuru, Manish Shrivastava, Mohit Bansal, Arjun Manoharan, Deepak Mittal, Preethi Jyothi, Yash Kumar Gupta
Publikováno v:
Proceedings of the Second Workshop on Scholarly Document Processing.
Large pretrained models have seen enormous success in extractive summarization tasks. In this work, we investigate the influence of pretraining on a BERT-based extractive summarization system for scientific documents. We derive significant performanc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c7b17e57f5744cdd0ffc0df98449722e
https://doi.org/10.18653/v1/2021.sdp-1.9
https://doi.org/10.18653/v1/2021.sdp-1.9
Publikováno v:
Ground-based and Airborne Telescopes VII.
The Segmented mirror technology has become natural choice for any optical telescope larger than 8 meter in size, where small mirror segments are aligned and positioned with respect to each other to an accuracy of few tens of nanometer. Primary mirror
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac7df0a152a00ec9e4264f7fd311ec0f
https://doi.org/10.1117/12.2313009
https://doi.org/10.1117/12.2313009