Transfer adaptation learning: A decade survey

L Zhang, X Gao - IEEE Transactions on Neural Networks and …, 2022 - ieeexplore.ieee.org
The world we see is ever-changing and it always changes with people, things, and the
environment. Domain is referred to as the state of the world at a certain moment. A research …

Big data: the end of the scientific method?

S Succi, PV Coveney - Philosophical Transactions of the …, 2019 - royalsocietypublishing.org
For it is not the abundance of knowledge, but the interior feeling and taste of things, which is
accustomed to satisfy the desire of the soul.(Saint Ignatius of Loyola). We argue that the …

Pre-train your loss: Easy bayesian transfer learning with informative priors

R Shwartz-Ziv, M Goldblum, H Souri… - Advances in …, 2022 - proceedings.neurips.cc
Deep learning is increasingly moving towards a transfer learning paradigm whereby large
foundation models are fine-tuned on downstream tasks, starting from an initialization …

[HTML][HTML] A population-based SHM methodology for heterogeneous structures: Transferring damage localisation knowledge between different aircraft wings

P Gardner, LA Bull, J Gosliga, J Poole, N Dervilis… - … Systems and Signal …, 2022 - Elsevier
Population-based structural health monitoring (PBSHM) offers a new viewpoint for structural
health monitoring (SHM), allowing diagnostic information to be shared across populations of …

Parallel transport on the cone manifold of SPD matrices for domain adaptation

O Yair, M Ben-Chen, R Talmon - IEEE Transactions on Signal …, 2019 - ieeexplore.ieee.org
In this paper, we consider the problem of domain adaptation. We propose to view the data
through the lens of covariance matrices and present a method for domain adaptation using …

Autonomous efficient experiment design for materials discovery with Bayesian model averaging

A Talapatra, S Boluki, T Duong, X Qian… - Physical Review …, 2018 - APS
The accelerated exploration of the materials space in order to identify configurations with
optimal properties is an ongoing challenge. Current paradigms are typically centered …

Transferring activity recognition models for new wearable sensors with deep generative domain adaptation

A Akbari, R Jafari - Proceedings of the 18th International Conference on …, 2019 - dl.acm.org
Wearable sensors provide enormous opportunities to identify activities and events of interest
for various applications. However, a major limitation of the current systems is the fact that …

Unlabelled data improves bayesian uncertainty calibration under covariate shift

A Chan, A Alaa, Z Qian… - … on machine learning, 2020 - proceedings.mlr.press
Modern neural networks have proven to be powerful function approximators, providing state-
of-the-art performance in a multitude of applications. They however fall short in their ability to …

Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data

E Hajiramezanali, S Zamani Dadaneh… - Advances in …, 2018 - proceedings.neurips.cc
Precision medicine aims for personalized prognosis and therapeutics by utilizing recent
genome-scale high-throughput profiling techniques, including next-generation sequencing …

Discriminative and geometry-aware unsupervised domain adaptation

L Luo, L Chen, S Hu, Y Lu… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Domain adaptation (DA) aims to generalize a learning model across training and testing
data despite the mismatch of their data distributions. In light of a theoretical estimation of the …