[HTML][HTML] Ten deep learning techniques to address small data problems with remote sensing

A Safonova, G Ghazaryan, S Stiller… - International Journal of …, 2023‏ - Elsevier
Researchers and engineers have increasingly used Deep Learning (DL) for a variety of
Remote Sensing (RS) tasks. However, data from local observations or via ground truth is …

Auditing large language models: a three-layered approach

J Mökander, J Schuett, HR Kirk, L Floridi - AI and Ethics, 2024‏ - Springer
Large language models (LLMs) represent a major advance in artificial intelligence (AI)
research. However, the widespread use of LLMs is also coupled with significant ethical and …

The need to separate the wheat from the chaff in medical informatics: Introducing a comprehensive checklist for the (self)-assessment of medical AI studies

F Cabitza, A Campagner - International Journal of Medical Informatics, 2021‏ - Elsevier
This editorial aims to contribute to the current debate about the quality of studies that apply
machine learning (ML) methodologies to medical data to extract value from them and …

The importance of being external. methodological insights for the external validation of machine learning models in medicine

F Cabitza, A Campagner, F Soares… - Computer methods and …, 2021‏ - Elsevier
Abstract Background and Objective Medical machine learning (ML) models tend to perform
better on data from the same cohort than on new data, often due to overfitting, or co-variate …

Targeted validation: validating clinical prediction models in their intended population and setting

M Sperrin, RD Riley, GS Collins, GP Martin - Diagnostic and prognostic …, 2022‏ - Springer
Clinical prediction models must be appropriately validated before they can be used. While
validation studies are sometimes carefully designed to match an intended population/setting …

[HTML][HTML] Comparing handcrafted features and deep neural representations for domain generalization in human activity recognition

N Bento, J Rebelo, M Barandas, AV Carreiro… - Sensors, 2022‏ - mdpi.com
Human Activity Recognition (HAR) has been studied extensively, yet current approaches are
not capable of generalizing across different domains (ie, subjects, devices, or datasets) with …

Multiscale data-driven seismic full-waveform inversion with field data study

S Feng, Y Lin, B Wohlberg - IEEE transactions on geoscience …, 2021‏ - ieeexplore.ieee.org
Seismic full-waveform inversion (FWI), which uses iterative methods to estimate high-
resolution subsurface models from seismograms, is a powerful imaging technique in …

[HTML][HTML] The challenges of using machine learning models in psychiatric research and clinical practice

D Ostojic, PA Lalousis, G Donohoe… - European …, 2024‏ - Elsevier
To understand the complex nature of heterogeneous psychiatric disorders, scientists and
clinicians are required to employ a wide range of clinical, endophenotypic, neuroimaging …

[HTML][HTML] Beyond here and now: Evaluating pollution estimation across space and time from street view images with deep learning

R Nathvani, D Vishwanath, SN Clark, AS Alli… - Science of the total …, 2023‏ - Elsevier
Advances in computer vision, driven by deep learning, allows for the inference of
environmental pollution and its potential sources from images. The spatial and temporal …

Statistics in the service of science: Don't let the tail wag the dog

H Singmann, D Kellen, GE Cox… - Computational Brain & …, 2023‏ - Springer
Statistical modeling is generally meant to describe patterns in data in service of the broader
scientific goal of develo** theories to explain those patterns. Statistical models support …