Domain Adaptation Problem

Redko, Ievgen; Habrard, Amaury; Morvant, Emilie; Sebban, Marc; Bennani, Younès

doi:10.1016/b978-1-78548-236-6.50002-7

Cited by 33 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It had shown a minimum deviation for 97% of the spectral set. Since Mahalanobis distance approach relies on the reasonable intuition that a good similarity function should assign a large (respectively small) score to pairs of points of the same class, as illustrated in Fig 7 we can conclude that the platelet spectra are highly homogeneous [ 17 ].…”

Section: Resultsmentioning

confidence: 99%

Spectral homogeneity of human platelets investigated by SERS

et al. 2022

View full text Add to dashboard Cite

This paper describes a detailed study of the spectral homogeneity of human platelets using Surface-enhanced Raman spectroscopy (SERS). We used a combined approach based on multivariate methods as principal component analysis and pair correlation algorithms to investigate platelets spectral properties. The correlation coefficients for each sample have been calculated, and the average coefficient of determination has been estimated. The high degree of spectral homogeneity inside one probe and between them has been revealed. The prospects of obtained results usage for pathologies based on platelet conformations during cardiovascular diseases have been demonstrated.

show abstract

Section: Resultsmentioning

confidence: 99%

Spectral homogeneity of human platelets investigated by SERS

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Although it is always possible, in principle, to acquire more experimental data, in practice the amount of data is unlikely to change because the cost is too high. In the laser pattern case, one possibility to circumvent this limitation is to combine data from experiments on several materials using domain adaptation [ 84 ], which would increase data by an order of magnitude and open the door to exploring patterns in unseen materials, which has great interest for applications.…”

Section: Discussionmentioning

confidence: 99%

Learning PDE to Model Self-Organization of Matter

Brandao

Colombier

Duffner

et al. 2022

Entropy

Self Cite

View full text Add to dashboard Cite

A self-organization hydrodynamic process has recently been proposed to partially explain the formation of femtosecond laser-induced nanopatterns on Nickel, which have important applications in optics, microbiology, medicine, etc. Exploring laser pattern space is difficult, however, which simultaneously (i) motivates using machine learning (ML) to search for novel patterns and (ii) hinders it, because of the few data available from costly and time-consuming experiments. In this paper, we use ML to predict novel patterns by integrating partial physical knowledge in the form of the Swift-Hohenberg (SH) partial differential equation (PDE). To do so, we propose a framework to learn with few data, in the absence of initial conditions, by benefiting from background knowledge in the form of a PDE solver. We show that in the case of a self-organization process, a feature mapping exists in which initial conditions can safely be ignored and patterns can be described in terms of PDE parameters alone, which drastically simplifies the problem. In order to apply this framework, we develop a second-order pseudospectral solver of the SH equation which offers a good compromise between accuracy and speed. Our method allows us to predict new nanopatterns in good agreement with experimental data. Moreover, we show that pattern features are related, which imposes constraints on novel pattern design, and suggest an efficient procedure of acquiring experimental data iteratively to improve the generalization of the learned model. It also allows us to identify the limitations of the SH equation as a partial model and suggests an improvement to the physical model itself.

show abstract

“…The potential relationship between data similarity and the generalization properties of ML models was first investigated from an empirical point of view in [ 20 ], where the authors discovered that datasets found to be substantially dissimilar likely stemmed from different distributions. Based on these findings, the authors of [ 21 ] demonstrated that information about similarity can be used to understand why a model performs poorly on a validation set, while the same information can be used to understand when and how to successfully perform domain adaptation (see, for example, the recent review [ 22 ]). To that end, several metrics for measuring data similarity have been proposed in the literature.…”

Section: Related Workmentioning

confidence: 99%

Comparing Handcrafted Features and Deep Neural Representations for Domain Generalization in Human Activity Recognition

Bento

Rebelo

Barandas

et al. 2022

Sensors

View full text Add to dashboard Cite

Human Activity Recognition (HAR) has been studied extensively, yet current approaches are not capable of generalizing across different domains (i.e., subjects, devices, or datasets) with acceptable performance. This lack of generalization hinders the applicability of these models in real-world environments. As deep neural networks are becoming increasingly popular in recent work, there is a need for an explicit comparison between handcrafted and deep representations in Out-of-Distribution (OOD) settings. This paper compares both approaches in multiple domains using homogenized public datasets. First, we compare several metrics to validate three different OOD settings. In our main experiments, we then verify that even though deep learning initially outperforms models with handcrafted features, the situation is reversed as the distance from the training distribution increases. These findings support the hypothesis that handcrafted features may generalize better across specific domains.

show abstract

Domain Adaptation Problem

Cited by 33 publications

References 0 publications

Spectral homogeneity of human platelets investigated by SERS

Spectral homogeneity of human platelets investigated by SERS

Learning PDE to Model Self-Organization of Matter

Comparing Handcrafted Features and Deep Neural Representations for Domain Generalization in Human Activity Recognition

Contact Info

Product

Resources

About