Results 51 to 60 of about 34,499 (218)
Time-frequency analysis for neural networks
Applied and Computational Harmonic AnalysisWe develop a quantitative approximation theory for shallow neural networks using tools from time-frequency analysis. Working in weighted modulation spaces $M^{p,q}_m(\mathbf{R}^{d})$, we prove dimension-independent approximation rates in Sobolev norms $W^{n,r}(Ω)$ for networks whose units combine standard activations with localized time-frequency ...
Ahmed Abdeljawad, Elena Cordero
openaire +2 more sources
Phosphoinositides and inositol phosphates as molecular glues
FEBS Letters, EarlyView.Inositol phosphates (IPs) and phosphoinositides (PIPs) regulate diverse eukaryotic processes. Beyond recruiting signaling proteins or acting as structural cofactors, recent studies suggest they mediate protein–protein interactions as natural molecular glues.
Aleshia Seaton‐Terry +9 more
wiley +1 more source
FEBS Letters, EarlyView.Inositol pyrophosphates are energy‐rich signaling molecules that perform critical functions in cells. Three different families of phosphatases hydrolyze the β phosphate of the inositol pyrophosphate molecules: two have narrow specificities and one is promiscuous.
Ronda J. Rolfes
wiley +1 more source
Time-series analysis with smoothed Convolutional Neural Network
Journal of Big Data, 2022 CNN originates from image processing and is not commonly known as a forecasting technique in time-series analysis which depends on the quality of input data. One of the methods to improve the quality is by smoothing the data.
Aji Prasetya Wibawa +5 more
doaj +1 more source
Structural Analysis of Sparse Neural Networks
Procedia Computer Science, 2019 Sparse Neural Networks regained attention due to their potential for mathematical and computational advantages. We give motivation to study Artificial Neural Networks (ANNs) from a network science perspective, provide a technique to embed arbitrary Directed Acyclic Graphs into ANNs and report study results on predicting the performance of image ...
Julian Stier, Michael Granitzer
openaire +2 more sources
Modelling stem cell differentiation related processes—A practical overview for biologists
FEBS Letters, EarlyView.Stem cell differentiation is complex and difficult to control experimentally. This review introduces suitable computational modelling approaches that can support stem cell research, from mechanistic ODE and abstract models to multiscale and deep learning methods.
Ricco Zeegelaar +4 more
wiley +1 more source
A Simple Neural Network for Estimating Fine Sediment Sources Using XRF and XRD
HydrologySuspended sediment (SS) has a wide range of negative effects such as increased water turbidity, altered habitat structures, sedimentation, and effects on hydraulic systems and environmental engineering projects.
Selline Mutiso +2 more
doaj +1 more source
White Noise Analysis of Neural Networks
CoRR, 2019 A white noise analysis of modern deep neural networks is presented to unveil their biases at the whole network level or the single neuron level. Our analysis is based on two popular and related methods in psychophysics and neurophysiology namely classification images and spike triggered analysis.
Ali Borji, Sikun Lin
openaire +3 more sources
FEBS Letters, EarlyView.CT10 regulator of kinase (CRK) and CRK‐Like (CRKL) are signaling adaptors driving cell adhesion, motility, differentiation, and proliferation. SH2‐domain containing (SH) proteins are enriched in YXXP motifs which when phosphorylated create preferred binding sites for CRK family SH2 domains.
Phoebe M. Cousens +8 more
wiley +1 more source