1 code implementation • 21 Jan 2023 • Anoop Kadan, Deepak P., Sahely Bhadra, Manjary P. Gangan, Lajish V. L
Groundbreaking inventions and highly significant performance improvements in deep learning based Natural Language Processing are witnessed through the development of transformer based large Pre-trained Language Models (PLMs).
1 code implementation • 27 Aug 2021 • Riikka Huusari, Sahely Bhadra, Cécile Capponi, Hachem Kadri, Juho Rousu
In this paper, instead of using the traditional representer theorem, we propose to search for a solution in RKHS that has a pre-image decomposition in the original data space, where the elements don't necessarily correspond to the elements in the training set.
1 code implementation • 9 Jan 2020 • Timothy LaRock, Timothy Sakharov, Sahely Bhadra, Tina Eliassi-Rad
We call this querying process Network Online Learning and present a family of algorithms called NOL*.
no code implementations • 12 Jun 2019 • Abilasha S, Sahely Bhadra, Deepak P, Anish Mathew
These two challenges make it hard to detect anomalies in time series as often such warpings could get detected as anomalies erroneously.
2 code implementations • 8 Feb 2016 • Sahely Bhadra, Samuel Kaski, Juho Rousu
In this paper, we introduce the first method that (1) can complete kernel matrices with completely missing rows and columns as opposed to individual missing kernel values, (2) does not require any of the kernels to be complete a priori, and (3) can tackle non-linear kernels.