Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s10620-020-06558-y | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Deep neural networks have an inbuilt Occam's razor.
Nat Commun
January 2025
Rudolf Peierls Centre for Theoretical Physics, University of Oxford, Oxford, UK.
The remarkable performance of overparameterized deep neural networks (DNNs) must arise from an interplay between network architecture, training algorithms, and structure in the data. To disentangle these three components for supervised learning, we apply a Bayesian picture based on the functions expressed by a DNN. The prior over functions is determined by the network architecture, which we vary by exploiting a transition between ordered and chaotic regimes.
View Article and Find Full Text PDFBest holdout assessment is sufficient for cancer transcriptomic model selection.
Patterns (N Y)
December 2024
Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, USA.
Guidelines in statistical modeling for genomics hold that simpler models have advantages over more complex ones. Potential advantages include cost, interpretability, and improved generalization across datasets or biological contexts. We directly tested the assumption that small gene signatures generalize better by examining the generalization of mutation status prediction models across datasets (from cell lines to human tumors and vice versa) and biological contexts (holding out entire cancer types from pan-cancer data).
View Article and Find Full Text PDFPCA-based spatial domain identification with state-of-the-art performance.
Bioinformatics
January 2025
Institute of Medical Systems Biology, Center for Biomedical AI (bAIome), Center for Molecular Neurobiology (ZMNH), University Medical Center Hamburg-Eppendorf, 20251, Hamburg, Germany.
Motivation: The identification of biologically meaningful domains is a central step in the analysis of spatial transcriptomic data.
Results: Following Occam's razor, we show that a simple PCA-based algorithm for unsupervised spatial domain identification rivals the performance of ten competing state-of-the-art methods across six single-cell spatial transcriptomic datasets. Our reductionist approach, NichePCA, provides researchers with intuitive domain interpretation and excels in execution speed, robustness, and scalability.
Causality-Driven Feature Selection for Calibrating Low-Cost Airborne Particulate Sensors Using Machine Learning.
Sensors (Basel)
November 2024
Department of Physics, University of Texas at Dallas, Richardson, TX 75080, USA.
With escalating global environmental challenges and worsening air quality, there is an urgent need for enhanced environmental monitoring capabilities. Low-cost sensor networks are emerging as a vital solution, enabling widespread and affordable deployment at fine spatial resolutions. In this context, machine learning for the calibration of low-cost sensors is particularly valuable.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!