Search alternatives:
algorithm both » algorithm blood (Expand Search), algorithm b (Expand Search), algorithm etc (Expand Search)
algorithm pre » algorithm where (Expand Search), algorithm used (Expand Search), algorithm from (Expand Search)
both function » body function (Expand Search), growth function (Expand Search), beach function (Expand Search)
algorithm pca » algorithm a (Expand Search), algorithm cl (Expand Search), algorithm co (Expand Search)
pre function » spread function (Expand Search), sphere function (Expand Search), three function (Expand Search)
pca function » gpcr function (Expand Search), a function (Expand Search), fc function (Expand Search)
algorithm both » algorithm blood (Expand Search), algorithm b (Expand Search), algorithm etc (Expand Search)
algorithm pre » algorithm where (Expand Search), algorithm used (Expand Search), algorithm from (Expand Search)
both function » body function (Expand Search), growth function (Expand Search), beach function (Expand Search)
algorithm pca » algorithm a (Expand Search), algorithm cl (Expand Search), algorithm co (Expand Search)
pre function » spread function (Expand Search), sphere function (Expand Search), three function (Expand Search)
pca function » gpcr function (Expand Search), a function (Expand Search), fc function (Expand Search)
-
1
-
2
Prediction performance of different optimization algorithms.
Published 2021“…<p>(A) 3 algorithms were compared in terms of the residuals of the cost function of the optimized TF on 7 mice datasets (Derivative free algorithm failed in optimizing a TF in a mouse). …”
-
3
Comparison of deconvolution and optimization algorithms on a batch of data.
Published 2021“…Output is given by the vascular response, measured as the change in speed of red blood cells flowing inside a capillary proximal to the recorded neuronal activation (in yellow, right panel). Both experimental data have been resampled at 50ms and used to compute a set of TFs (in orange) either with direct deconvolution approaches (Fourier or Toeplitz methods, middle-upper panel TFs) or with 1-Γ function optimization performed by 3 different algorithms (middle-lower panel TFs). …”
-
4
-
5
Feature selection algorithm.
Published 2023“…Our analysis pipeline included pre-processing steps, feature extraction from both time and frequency domains, a voting algorithm for selecting features, and model training and validation. …”
-
6
-
7
Reconstructing <i>sparse</i>, binary patterns using message passing algorithms and PCA.
Published 2023“…<p>We plot the mse per pattern obtained by the AMP algorithm, <a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1010813#pcbi.1010813.e072" target="_blank">Eq (32)</a>, as a function of the effective noise Δ (<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1010813#pcbi.1010813.e032" target="_blank">9</a>), for random (<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1010813#pcbi.1010813.e044" target="_blank">15</a>) and informed (<a href="http://www.ploscompbiol.org/article/info:doi/10.1371/journal.pcbi.1010813#pcbi.1010813.e045" target="_blank">16</a>) initialisations. …”
-
8
-
9
Functional PCA With Covariate-Dependent Mean and Covariance Structure
Published 2022“…<p>Incorporating covariates into functional principal component analysis (PCA) can substantially improve the representation efficiency of the principal components and predictive performance. …”
-
10
-
11
-
12
As for Fig 2, we present failure rates as a function of the cohort size (vertical axis) versus the number of distractors (horizontal axis), for the Smyth and McClave baseline algor...
Published 2020“…<p>We explore the behaviour of the baseline algorithm both in terms of whether it can recover maximally diverse cohorts (upper four panels), and whether it can recover imbalanced cohorts. …”
-
13
-
14
-
15
-
16
-
17
-
18
-
19
-
20