Results 71 to 80 of about 246,254 (290)

Amortized Generation of Sequential Algorithmic Recourses for Black-Box Models

Proceedings of the AAAI Conference on Artificial Intelligence, 2022
Explainable machine learning (ML) has gained traction in recent years due to the increasing adoption of ML-based systems in many sectors. Algorithmic Recourses (ARs) provide "what if" feedback of the form "if an input datapoint were x' instead of x, then an ML-based system's output would be y' instead of y." Recourses are attractive due to their ...
Sahil Verma 0003, Keegan Hines, John P. Dickerson   +2 more
openaire   +2 more sources

PAK1 activation drives divergent resistance mechanisms to aromatase inhibition and tamoxifen in a luminal: A breast cancer model

Molecular Oncology, EarlyView.
Breast cancer remains a major cause of cancer death in women, frequently developing endocrine therapy resistance. This study demonstrates that upregulated p21‐activated kinase 1 (PAK1) activity drives resistance to tamoxifen and long‐term estrogen deprivation in ER+ breast cancer models.
Luisa Schwarzmüller, Janina Müller, Efstathios‐Iason Vlachavas, Lukas Beumers, Lena Fleischhacker, Sara Burmester, Angelika Wörner, Sabine Karolus, Dominic Helm, Cindy Körner, Stefan Wiemann   +10 more
wiley   +1 more source

When is black-box AI justifiable to use in healthcare?

Big Data & Society
Although it is reasonable and valuable to seek explanations for decisions made by artificial intelligence (AI), it is simply not possible with black-box AI algorithms.
Sinead Prince, Julian Savulescu
doaj   +1 more source

Aging Study of In-Use Lithium-Ion Battery Packs to Predict End of Life Using Black Box Model

Applied Sciences, 2022
In order to study the state of health (SOH) of unbalanced battery packs in real life, a thorough analysis is carried out using only data available and standard charging material.
Daniela Chrenko, Manuel Fernandez Montejano, Sudnya Vaidya, Romain Tabusse   +3 more
doaj   +1 more source

A Comparison of Global Search Algorithms for Continuous Black Box Optimization [PDF]

Evolutionary Computation, 2012
Four methods for global numerical black box optimization with origins in the mathematical programming community are described and experimentally compared with the state of the art evolutionary method, BIPOP-CMA-ES. The methods chosen for the comparison exhibit various features that are potentially interesting for the evolutionary computation community:
Pošík, Petr, Huyer, Waltraud, Pál, Lászlo   +2 more
openaire   +3 more sources

Polarization‐resolved femtosecond Vis/IR spectroscopy tailored for resolving weak signals in biological samples using minimal sample volume

FEBS Open Bio, EarlyView.
Unique biological samples, such as site‐specific mutant proteins, are available only in limited quantities. Here, we present a polarization‐resolved transient infrared spectroscopy setup with referencing to improve signal‐to‐noise tailored towards tracing small signals. We provide an overview of characterizing the excitation conditions for polarization‐
Clark Zahn, Karsten Heyne
wiley   +1 more source

Black-Box Universal Adversarial Attack for DNN-Based Models of SAR Automatic Target Recognition

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep neural networks (DNNs) are vulnerable to attacks of adversarial examples. Universal adversarial attack algorithms can help evaluate and improve the robustness of the SAR-
Xuanshen Wan, Wei Liu, Chaoyang Niu, Wanjie Lu, Meng Du, Yuanli Li   +5 more
doaj   +1 more source

Dix petits hacks Tinder : les algorithmes au service d’une économie spéculative des rencontres amoureuses et sexuelles

Tic & Société, 2021
The mediation of love and sexuality has often relied on dating advice. This paper analyses a corpus of dating guides concerning the popular app Tinder. Our analysis suggests that the practice of algorithmic blackboxing, that is, characterizing algorithms
David MYLES, Martin BLAIS
doaj   +1 more source

Molecular dynamics simulations of positively selected codons in FcγRI reveal novel biochemical binding properties

FEBS Open Bio, EarlyView.
Evolutionary analysis across 32 placental mammals identified positive selection at residues H148 and W149 in the immune receptor FcγR1. Ancestral reconstruction combined with molecular dynamics simulations reveals how these mutations may influence receptor structure and dynamics, providing insight into the evolution of antibody recognition and immune ...
David A. Young, Omar Arias‐Gaguancela, Fiona Gibson, Morgan Grainger, Jodie Score, Amit Nathubhai, Mauricio Cafiero, Lee Richard Machado   +7 more
wiley   +1 more source

Interpretable machine learning models for hospital readmission prediction: a two-step extracted regression tree approach

BMC Medical Informatics and Decision Making, 2023
Background Advanced machine learning models have received wide attention in assisting medical decision making due to the greater accuracy they can achieve. However, their limited interpretability imposes barriers for practitioners to adopt them.
Xiaoquan Gao, Sabriya Alam, Pengyi Shi, Franklin Dexter, Nan Kong   +4 more
doaj   +1 more source