Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Ankita Shukla"'
Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher network) to train a smaller model (student network). Recently, addition
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7083efe01cc38151dd87ba3cbb4d390
http://arxiv.org/abs/2302.14130
http://arxiv.org/abs/2302.14130
Publikováno v:
Ankita Shukla
Deep neural networks have increasingly been used as an auxiliary tool in healthcare applications, due to their ability to improve performance of several diagnosis tasks. However, these methods are not widely adopted in clinical settings due to the pr
Publikováno v:
IEEE Internet Things J
Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number of parameters makes it difficult to integrate these models into edge de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7d0cd726c3baf6be512481d1cf814475
Publikováno v:
ICVGIP
Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these latent spaces h
Publikováno v:
BigMM
Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learning or their dependence on la
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2542356b0ed28f17d235afa7cf160c0b
http://arxiv.org/abs/1806.01547
http://arxiv.org/abs/1806.01547
Publikováno v:
ICPR
In this paper we address the problem of recovering a matrix, with inherent low rank structure, from its lower dimensional projections. This problem is frequently encountered in wide range of areas including pattern recognition, wireless sensor networ
Autor:
Ankita Shukla, Rushil Anirudh, Eugene Kur, Thiagarajan, Jayaraman J., Peer-Timo Bremer, Spears, Brian K., Tammy Ma, Turaga, Pavan K.
Publikováno v:
Ankita Shukla
In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion. Unlike a typical hyperspherical generative model that requires computationally inefficient sa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::48715514fcb6902efb7874b925604811
https://arxiv.org/abs/2111.12798
https://arxiv.org/abs/2111.12798
Autor:
John Kevin Cava, Vant, John W., Nicholas Ho, Ankita Shukla, Turaga, Pavan K., Ross Maciejewski, Abhishek Singharoy
Publikováno v:
Ankita Shukla
In this paper, we utilized generative models, and reformulate it for problems in molecular dynamics (MD) simulation, by introducing an MD potential energy component to our generative model. By incorporating potential energy as calculated from TorchMD
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2fb1974cd56704363a896f3bd785bd8f
https://arxiv.org/abs/2111.14053
https://arxiv.org/abs/2111.14053