fourier-features

A library of scalable Bayesian generalised linear models with fancy features

Image classification using SVM, KNN, Bayes, Adaboost, Random Forest and CNN.Extracting features and reducting feature dimension using T-SNE, PCA, LDA.

Unofficial pytorch implementation of the paper "Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding", NeurIPS 2021.

Implementation of two phase field approaches for the surface reconstruction problem. One based of the Modica-Mortola theorem and the other based on Ambrosio-Tortorelli | Master Thesis

Incremental Sparse Spectrum Gaussian Process Regression

Sparse spectrum Gaussian process regression

AG-MAE: Anatomically Guided Spatio-Temporal Masked Auto-Encoder for Online Hand Gesture Recognition

Aplicación web para calcular y graficar series, integral, transformada y transformada discreta de Fourier, así como transformada de Laplace y resolver EDOs

Multi-Architecture Coupled Ensemble Physics-Informed Neural Networks (MACE-PINN) for solving coupled partial differential equations. Implements parallel subnetworks with Fourier embeddings and adaptive loss weighting for Gray-Scott and Ginzburg-Landau reaction-diffusion systems.

SCFGP: Sparsely Correlated Fourier Features Based Gaussian Process

Time series regression modeling on a dataset of supermarket sales across years, with the Darts library in Python.

Forecasting Store Sales for Improved Decision-Making Using Machine Learning for Time Series Data

Tensorflow 2.0 implementation of fourier feature mapping networks.

Neural Fields for Sea Surface Height Interpolation.

O E-COMPRESS é um sistema híbrido de compressão de arquivos que combina redes neurais supervisionadas com técnicas tradicionais como gzip e validação de integridade por CRC e ECC. Ele segmenta arquivos em blocos independentes, codifica cada um com Fourier Features e redes MLP, e reconstrói com alta fidelidade.

PyTorch implementation of a receiver query neural surrogate for surface seismogram emulation in heterogeneous 2D acoustic media. Includes Fourier encoded receiver coordinates, balanced sampling, a masked pseudo physics informed trace loss, and evaluation tools

Learned Nyquist: fundamental aliasing limits of implicit neural representations (IEEE ICASSP SPTM). Achievability + converse, Monte-Carlo-validated, real data both sides.

Image regression experiments with random fourier feature mapping using PyTorch

A Modern Spin on Ptolemy's Geocentric Universe Model

Visualizing function fittings