155 skills found · Page 4 of 6
sintefore / PiecewiseAffineApprox.jlCompute and add convex (or concave) piecewise linear approximations of functions or a set of points to optimization models modelled in JuMP
NTimmons / FastActivations.jlA collection of activation function approximations for Flux.
zahraabashir / RBF Function ApproximationTraining an RBF(Radial Basis Function) Neural Network for function approximation. (2019)
AdrianLiu00 / DIF LUT ToolToolchain of DIF-LUT for the approximation of nonlinear functions.
shabbychef / PDQutilsPDQ Functions via Gram-Charlier, Edgeworth, and Cornish-Fisher Approximations
sfilip / EmethodAn automatic tool for the evaluation of polynomial and rational function approximations, complete with a hardware implementation for FPGAs
ahmed-touati / Convergent Off PolicyCode for the article "Convergent Tree-Backup and Retrace with Function Approximation".
sschott20 / ALibmGenerating correctly round elementary function approximations for floating point math libraries using a modified Remez algorithm.
hbertoduarte / Hilbert 2dRust functions for mapping between 1D and 2D space using the Hilbert curve, and its approximations.
josebarahonay / MFNNAn implementation of the multi-fidelity architecture proposed in "A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems"
HGGM-LIM / TracerkineticThis R package implements compartmental models and linear approximations needed to perform kinetic analysis on dynamic medical images. The provided functions use the tissue time-activity curves, the input function and the frame times as input, and return the kinetic parameters and the estimated errors.
tomasmckelvey / FsidFSID is an open source toolbox, implemented in the Python Julia and Matlab programming languages. FSID is a toolbox with scripts which estimates linear multi-input multi-output state-space models from sample data using frequency-domain subspace algorithms. Algorithms which estimate models based on samples of the transfer function matrix as well as frequency domain input and output vectors are provided. The algorithms can be used for discrete-time models, continuous-time models as well as for approximation of rational matrices from samples corresponding to arbitrary points in the complex plane.
Pressio / Pressio DemoappsSuite of 1D, 2D, 3D demo apps of varying complexity with built-in support for sample mesh and exact Jacobians
GeorgianBadita / Genetic Programming Function ApproximationPython framework to approximate mathemtical functions
dennisjc / Ann MtTrained network and auxillary files for neural network MT forward function approximation
LucasAlegre / Linear RlReinforcement Learning with linear function approximation
HariKrishnan06082k / Robot Learning For Planning And ControlTopics include function approximation, learning dynamics, using learned dynamics in control and planning, handling uncertainty in learned models, learning from demonstration, and model-based and model-free reinforcement learning.
panxulab / Distributionally Robust LSVI UCBCode for the paper "Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation", International Conference on Artificial Intelligence and Statistics (AISTATS) 2024
Breakend / CMACvTileCodeNo description available
Mechanics-Mechatronics-and-Robotics / Physics Based Loss And Machine Learning Approach In Application To Viscous Fluids Flow ModelingThe idea of taking the path of least resistance arose a long time ago, and people find its confirmation both in themselves and in the environment. Aristotle expressed this idea in his writings, Fermat used this idea to describe the law of refraction of light, and Maupertuis was the first to formulate the principle of least action in mechanics. The variational approach of finding the extremum of an objective functional is an alternative approach to the solution of partial differential equations in mechanics of continua. The great challenge in variational calculus direct methods is to find a set of functions that will be able to approximate the solution accurately enough. Artificial neural networks are powerful tools for approximation, and the physics-based functional can be the natural loss for a machine learning method. In this paper, we focus on the loss that may take non-linear fluid properties and mass forces into account. We modified the energy-based variational principle and determined the constraints on its unknown functions that implement boundary conditions. We explored artificial neural networks as an option for loss minimization and the approximation of the unknown function. We compared the obtained results with the known solutions. The proposed method allows modeling non-Newtonian fluids flow including blood, synthetic oils, paints, plastic, bulk materials, and even rheomagnetic fluids.
