In this article, the theory of multivariate max-product neural network (NN) and quasi-interpolation operators has been introduced. Pointwise and uniform approximation results have been proved, together with estimates concerning the rate of convergence. At the end, several examples of sigmoidal activation functions have been provided.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2016.06.002 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Alterations in the white matter fiber tracts of preschool-aged children with autism spectrum disorder: an automated fiber quantification study.
Quant Imaging Med Surg
December 2024
Department of Radiology, Children's Hospital of Chongqing Medical University, National Clinical Research Center for Child Health and Disorders, Ministry of Education Key Laboratory of Child Development and Disorders, Chongqing Key Laboratory of Child Neurodevelopment and Cognitive Disorders, Chongqing, China.
Background: Little is known about the precise impaired patterns of white matter (WM) fiber tracts in preschool-aged children with autism spectrum disorder (ASD). Thus, we used diffusion tensor imaging (DTI)-based automated fiber quantification (AFQ) to explore the changes in WM fiber tracts in preschool-aged children with ASD and its correlation with the severity of clinical manifestations.
Methods: A total of 43 pediatric ASD and 42 age- and sex-matched typical developing children were examined with DTI.
Multi-Biometric Feature Extraction from Multiple Pose Estimation Algorithms for Cross-View Gait Recognition.
Sensors (Basel)
November 2024
Department of Computer Science and Digital Technologies, University of East London, London E16 2RD, UK.
Gait recognition is a behavioral biometric technique that identifies individuals based on their unique walking patterns, enabling long-distance identification. Traditional gait recognition methods rely on appearance-based approaches that utilize background-subtracted silhouette sequences to extract gait features. While effective and easy to compute, these methods are susceptible to variations in clothing, carried objects, and illumination changes, compromising the extraction of discriminative features in real-world applications.
View Article and Find Full Text PDFGlymphatic function assessment with diffusion tensor imaging along the perivascular space in patients with major depressive disorder and its relation to cerebral white-matter alteration.
Quant Imaging Med Surg
September 2024
Department of Radiology, the First Affiliated Hospital of Dalian Medical University, Dalian, China.
Article Synopsis
- This study investigates the connection between the glymphatic system's function and white matter changes in individuals with major depressive disorder (MDD) through advanced imaging techniques.
- Researchers recruited 35 MDD patients and 23 healthy controls, assessing their brain structure and neuropsychological factors with methods like diffusion tensor imaging and various clinical rating scales.
- Findings revealed that MDD patients had significantly lower glymphatic function scores compared to healthy individuals, indicating a potential link between glymphatic dysfunction and depression severity.
Noncompact uniform universal approximation.
Neural Netw
May 2024
TU Delft, EWI/DIAM, P.O. Box 5031, 2600 GA Delft, The Netherlands. Electronic address:
The universal approximation theorem is generalised to uniform convergence on the (noncompact) input space R. All continuous functions that vanish at infinity can be uniformly approximated by neural networks with one hidden layer, for all activation functions φ that are continuous, nonpolynomial, and asymptotically polynomial at ±∞. When φ is moreover bounded, we exactly determine which functions can be uniformly approximated by neural networks, with the following unexpected results.
View Article and Find Full Text PDFVarious techniques in microscopy are based on point-wise acquisition, which provides advantages in acquiring sectioned images, for example in confocal or two-photon microscopy. The advantages come along with the need to perform three-dimensional scanning, which is often realized by mechanical movement achieved by stage-scanning or piezo-based scanning in the axial direction. Lateral scanning often employs galvo-mirrors, leading to a reflective setup and hence to a folded beam path.
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!