User profiles for Ashwin De Silva

Ashwin De Silva

PhD Student, Johns Hopkins University
Verified email at jhu.edu
Cited by 100

Prospective Learning: Learning for a Dynamic Future

A De Silva, R Ramesh, R Yang, S Yu… - Advances in …, 2025 - proceedings.neurips.cc
In real-world applications, the distribution of the data, and our goals, evolve over time. The
prevailing theoretical framework for studying machine learning, namely probably …

A joint convolutional and spatial quad-directional lstm network for phase unwrapping

MV Perera, A De Silva - Icassp 2021-2021 ieee international …, 2021 - ieeexplore.ieee.org
Phase unwrapping is a classical ill-posed problem which aims to recover the true phase
from wrapped phase. In this paper, we introduce a novel Convolutional Neural Network (CNN) …

Real-time hand gesture recognition Using temporal muscle activation maps of multi-channel sEMG signals

A De Silva, MV Perera… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
Accurate and real-time hand gesture recognition is essential for controlling advanced hand
prostheses. Surface Electromyography (sEMG) signals obtained from the forearm are widely …

The value of out-of-distribution data

A De Silva, R Ramesh, C Priebe… - International …, 2023 - proceedings.mlr.press
Generalization error always improves with more in-distribution data. However, it is an open
question what happens as we add out-of-distribution (OOD) data. Intuitively, if the OOD data …

Towards accurate cross-domain in-bed human pose estimation

…, M Anandakumar, A De Silva… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Human behavioral monitoring during sleep is essential for various medical applications.
Majority of the contactless human pose estimation algorithms are based on RGB modality, …

Low-cost active dry-contact surface emg sensor for bionic arms

AM Naim, K Wickramasinghe, A De Silva… - … on Systems, Man …, 2020 - ieeexplore.ieee.org
Surface electromyography (sEMG) is a popular bio-signal used for controlling prostheses
and finger gesture recognition mechanisms. Myoelectric prostheses are costly, and most …

A thickness sensitive vessel extraction framework for retinal and conjunctival vascular tortuosity analysis

A De Silva, MV Perera, N Wijethilake… - arXiv preprint arXiv …, 2021 - arxiv.org
Systemic diseases such as diabetes, hypertension, atherosclerosis are among the leading
causes of annual human mortality rate. It is suggested that retinal and conjunctival vascular …

Prospective learning: Principled extrapolation to the future

A De Silva, R Ramesh, L Ungar… - Conference on …, 2023 - proceedings.mlr.press
Learning is a process which can update decision rules, based on past experience, such that
future performance improves. Traditionally, machine learning is often evaluated under the …

Approximately optimal domain adaptation with fisher's linear discriminant

H Helm, A De Silva, JT Vogelstein, CE Priebe, W Yang - Mathematics, 2024 - mdpi.com
We propose and study a data-driven method that can interpolate between a classical and a
modern approach to classification for a class of linear models. The class is the convex …

[PDF][PDF] Out-of-distribution detection using kernel density polytopes

J Dey, A De Silva, W LeVine, J Shin, H Xu… - arXiv preprint arXiv …, 2022 - academia.edu
Any reasonable machine learning (ML) model should not only interpolate efficiently in between
the training samples provided (in-distribution region), but also approach the extrapolative …