Results 141 to 150 of about 13,735 (297)
Shortcut Detection With Variational Autoencoders
2024 International Joint Conference on Neural Networks (IJCNN)For real-world applications of machine learning (ML), it is essential that models make predictions based on well-generalizing features rather than spurious correlations in the data. The identification of such spurious correlations, also known as shortcuts, is a challenging problem and has so far been scarcely addressed. In this work, we present a novel
Nicolas M. Müller +4 more
openaire +2 more sources
Data‐Guided Photocatalysis: Supervised Machine Learning in Water Splitting and CO2 Conversion
Advanced Intelligent Discovery, EarlyView.This review highlights recent advances in supervised machine learning (ML) for photocatalysis, emphasizing methods to optimize photocatalyst properties and design materials for solar‐driven water splitting and CO2 reduction. Key applications, challenges, and future directions are discussed, offering a practical framework for integrating ML into the ...
Paul Rossener Regonia +1 more
wiley +1 more source
Advanced Intelligent Discovery, EarlyView.Sequential multicolor fluorescence imaging in dynamic microsystems is constrained by acquisition speed and excitation dose. This study introduces a real‐time framework to reconstruct spectrally separated channels from reduced cross‐channel acquisitions (frames containing mixed spectral contributions).
Juan J. Huaroto +3 more
wiley +1 more source
Autoencoders in Natural Language Processing: A Comprehensive Review
ComputersAutoencoder-based models have become a fundamental component of unsupervised and self-supervised learning in natural language processing (NLP), enabling models to learn compact latent representations through input reconstruction.
Moussa Redah, Wasfi G. Al-Khatib
doaj +1 more source
Machine Learning Driven Inverse Design of Broadband Acoustic Superscattering
Advanced Intelligent Discovery, EarlyView.Multilayer acoustic superscatterers are designed using machine learning to achieve broadband superscattering and strong sound insulation. By incorporating a weighted mean absolute error into the loss function, the forward and inverse neural networks accurately map structural parameters to spectral responses.
Lijuan Fan, Xiangliang Zhang, Ying Wu
wiley +1 more source
M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood [PDF]
, 2019 Korthals T. M²VAE - Derivation of a Multi-Modal Variational Autoencoder Objective from the Marginal Joint Log-Likelihood. arXiv: 1903.07303v1. 2019.This work gives an in-depth derivation of the trainable evidence lower bound obtained from the marginal ...
Korthals, Timo ; https://orcid.org/
core +1 more source
Composition‐Aware Cross‐Sectional Integration for Spatial Transcriptomics
Advanced Intelligent Discovery, EarlyView.Multi‐section spatial transcriptomics demands coherent cell‐type deconvolution, domain detection, and batch correction, yet existing pipelines treat these tasks separately. FUSION unifies them within a composition‐aware latent framework, modeling reads as cell‐type–specific topics and clustering in embedding space.
Qishi Dong +5 more
wiley +1 more source
Harnessing Machine Learning to Understand and Design Disordered Solids
Advanced Intelligent Discovery, EarlyView.This review maps the dynamic evolution of machine learning in disordered solids, from structural representations to generative modeling. It explores how deep learning and model explainability transform property prediction into profound physical insight.
Muchen Wang, Yue Fan
wiley +1 more source
VAE-Var: Variational-Autoencoder-Enhanced Variational Assimilation [PDF]
Data assimilation refers to a set of algorithms designed to compute the optimal estimate of a system's state by refining the prior prediction (known as background states) using observed data.
Bai, Lei +3 more
core +1 more source
Jointly Trained Variational Autoencoder for Multi-Modal Sensor Fusion [PDF]
, 2019 Korthals T, Hesse M, Leitner J, Melnik A, Rückert U. Jointly Trained Variational Autoencoder for Multi-Modal Sensor Fusion. In: 22st International Conference on Information Fusion, (FUSION) 2019, Ottawa, CA, July 2-5, 2019.
Hesse, Marc ; https://orcid.org/ +4 more
core +1 more source