We propose a variation of the self-organizing map algorithm by considering the random placement of neurons on a two-dimensional manifold, following a blue noise distribution from which various topologies can be derived. These topologies possess random (but controllable) discontinuities that allow for a more flexible self-organization, especially with high-dimensional data. The proposed algorithm is tested on one-, two- and three-dimensional tasks, as well as on the MNIST handwritten digits data set and validated using spectral analysis and topological data analysis tools. We also demonstrate the ability of the randomized self-organizing map to gracefully reorganize itself in case of neural lesion and/or neurogenesis.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1162/neco_a_01406 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Effects of photobiomodulation and bethanechol chloride treatment on salivary composition and flow rate in head and neck cancer patients undergoing radiotherapy: longitudinal interventional experimental clinical study.
Support Care Cancer
January 2025
Department of Stomatology, Federal University of Paraná, Av. Prefeito Lothário Meissner, 632, 80210-170, Curitiba, PR, Brazil.
Objective: To evaluate the efficacy of photobiomodulation therapy (PBMT) and bethanechol chloride (BC) on the quantity and quality of saliva in patients undergoing radiotherapy (RT) for head and neck cancer.
Methods: Saliva samples were collected from patients before and after RT, who were treated with PBMT or BC. Clinical parameters, including salivary flow rate (SFR), pH, xerostomia, and concentrations of macro and microelements in saliva, were assessed.
Visualising Analytes in Gas Chromatography by Staining and Substance Maps.
Talanta
January 2025
Institute of Chemistry of Renewable Resources, Department of Chemistry, BOKU University, Konrad-Lorenz-Straße 24, 3430, Tulln, Austria. Electronic address:
Chromatographic separations in combination with spectroscopic detectors are a main pillar of today's analytical chemistry. The recorded spectroscopic data is usually not shown in a typical chromatogram, therefore the contained additional information cannot be accessed readily by the analyst and is inspected in tedious additional routines, such as separate database searches. We developed a method to add colors to gas chromatograms with mass spectral detection.
View Article and Find Full Text PDFInsight into the abundance and optical characteristics of water-soluble organic compounds (WSOC) in PM in urban areas.
Chemosphere
January 2025
College of Design and Engineering, National University of Singapore, Singapore, 117576, Singapore. Electronic address:
Airborne particulate matter (PM) poses significant environmental and health challenges, particularly in urban areas. This study investigated the characteristics of water-soluble organic compounds (WSOC) in PM (PM with an aerodynamic diameter of 2.5 μm or less) in Singapore, a tropical Asian city-state, over a six-month period.
View Article and Find Full Text PDFThis study presents an integrated framework that combines spatial clustering techniques and multi-source geospatial data to comprehensively assess and understand geological hazards in Hunan Province, China. The research integrates self-organizing map (SOM) and geo-self-organizing map (Geo-SOM) to explore the relationships between environmental factors and the occurrence of various geological hazards, including landslides, slope failures, collapses, ground subsidence, and debris flows. The key findings reveal that annual average precipitation (Pre), profile curvature (Pro_cur), and slope (Slo) are the primary factors influencing the composite geological hazard index (GI) across the province.
View Article and Find Full Text PDFProbabilistic nested model selection in pharmacokinetic analysis of DCE-MRI data in animal model of cerebral tumor.
Sci Rep
January 2025
Department of Radiation Oncology, Henry Ford Hospital, Detroit, USA.
Best current practice in the analysis of dynamic contrast enhanced (DCE)-MRI is to employ a voxel-by-voxel model selection from a hierarchy of nested models. This nested model selection (NMS) assumes that the observed time-trace of contrast-agent (CA) concentration within a voxel, corresponds to a singular physiologically nested model. However, admixtures of different models may exist within a voxel's CA time-trace.
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!