Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Soumith Chintala"'
Autor:
Yao-Yuan Yang, Moto Hira, Zhaoheng Ni, Artyom Astafurov, Caroline Chen, Christian Puhrsch, David Pollack, Dmitriy Genzel, Donny Greenberg, Edward Z. Yang, Jason Lian, Jeff Hwang, Ji Chen, Peter Goldsborough, Sean Narenthiran, Shinji Watanabe, Soumith Chintala, Vincent Quenneville-Belair
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4887ccc876682fac0a02a1660efee100
https://doi.org/10.1109/icassp43922.2022.9747236
https://doi.org/10.1109/icassp43922.2022.9747236
Autor:
Ryan Drew, Sara Elkafrawy, Dhiraj Gandhi, Rebecca Qian, Anurag Pratik, Tucker Hart, Abhinav Gupta, Kavya Srinet, Arthur Szlam, Mary Williamson, Anoushka Tiwari, Soumith Chintala, Yuxuan Sun
Publikováno v:
ICRA
In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale. But most of these systems are: (a) isolated (perception, speech, or language only); (b) trained on static datasets. On the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1e24663a1684b05c0fccc76c0e65ba60
https://doi.org/10.1109/icra48506.2021.9561446
https://doi.org/10.1109/icra48506.2021.9561446
Autor:
Wojciech Zaremba, Mark Tygert, Soumith Chintala, Arthur Szlam, Marc'Aurelio Ranzato, Yuandong Tian
Publikováno v:
Applied and Computational Harmonic Analysis. 42:154-166
Multinomial logistic regression and other classification schemes used in conjunction with convolutional networks (convnets) were designed largely before the rise of the now standard coupling with convnets, stochastic gradient descent, and backpropaga
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc3e052a8a44ccb17fb45066d6af6c2e
https://doi.org/10.1016/j.acha.2016.06.005
https://doi.org/10.1016/j.acha.2016.06.005
Autor:
Misha Smelyanskiy, Pieter Noordhuis, Bill Jia, Soumith Chintala, Jason Lu, Kim Hazelwood, Xiaodong Wang, Dmytro Dzhulgakov, Sarah Bird, Mohamed Fawzy, Aditya Kalro, Utku Diril, Liang Xiong, Kevin M. Lee, David Brooks, James Law, Yangqing Jia
Publikováno v:
HPCA
Machine learning sits at the core of many essential products and services at Facebook. This paper describes the hardware and software infrastructure that supports machine learning at global scale. Facebook's machine learning workloads are extremely d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a46a75c32a0ee1751730f8f9f878337b
https://doi.org/10.1109/hpca.2018.00059
https://doi.org/10.1109/hpca.2018.00059
Publikováno v:
CVPR
This paper establishes the existence of observable footprints that reveal the "causal dispositions" of the object categories appearing in collections of images. We achieve this goal in two steps. First, we take a learning approach to observational ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c6f9e7bce66898dbd876f9130a2f6524
https://doi.org/10.1109/cvpr.2017.14
https://doi.org/10.1109/cvpr.2017.14
Autor:
Sergey Zagoruyko, Pedro O. Pinheiro, Sam Gross, Tsung-Yi Lin, Adam Lerer, Soumith Chintala, Piotr Dollár
Publikováno v:
BMVC
The recent COCO object detection dataset presents several new challenges for object detection. In particular, it contains objects at a broad range of scales, less prototypical images, and requires more precise localization. To address these challenge
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9e2c9add4f8d94131b507a276590b20
A complex-valued convolutional network (convnet) implements the repeated application of the following composition of three operations, recursively applying the composition to an input vector of nonnegative real numbers: (1) convolution with complex-v
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::62b88824033a9be955371fb97d904870
Publikováno v:
CVPR
Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::348ec434c88e0d8a4f7f765fb026a059
Autor:
A. Kannammal, Aditya Chopra, Devang Negandhi, V. Ramachandran, Soumith Chintala, N. Ch. S. N. Iyengar
Publikováno v:
International Journal of Electronic Business. 8:342
In this paper, we present an adaptive tutoring system for students of multiple domains with a web-based interface for flexibility. The displayed media is adapted according to the student's capability and aptitude by evaluating the student according t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::243184e11fc432853f24c6a0102c70d8
https://doi.org/10.1504/ijeb.2010.035291
https://doi.org/10.1504/ijeb.2010.035291