DeltaProduct is a new linear recurrent neural network architecture that uses products of generalized Householder matrices as state-transition matrices enabling better expressivity, state-tracking, and language modeling performance than DeltaNet.
Spectral Tensor Train Parameterization of Deep Learning Layers
Fortran routines from "Solving Least Squares Problems" by C. Lawson and R. Hanson (1995)
Parallelization of QR decomposition with Householder transformation
VDS is an AI-first FOSS meant for self hosting, LocalLLM that will let you scan your shopping recipts, keep track of what you have, and how much money you spent on what. Yes, it's vibecoded.
matrix decomposition from scratch for matrix analysis and analysis course capstone of ucas
Different methods to QR factorization
Numerical Methods for Ill-Conditioned Matrices - A project with Hilbert Matrix
Three algorithms (classical GS, modified GS, and Householder) for QR factorisation written in Julia. Included is a standard backsubstitution algorithm also for Julia.
HoHoMa-MyPurchase is meant to be a helping assistant when it comes to shopping. A pre-calculated shoppinglist for the day, reminders and automatic analysis of demands and stock.
Solving the Least Squares Problem via reduced QR factorization by Gram-Schmidt and by Householder triangularization.
PicturePrediction is based on machine-learning concepts, aiming to create automated predictions in relation with the nature of certain cats or non-containing cats pictures. Using a data set of given images, it may independently distinguish characteristics of a new picture with an accuracy up to 75%.
Householder reflection QR. System of linear equations.
Linear solvers and matrix computation
Supervised ML program which predicts with 65% accuracy whether there is a cat in a given picture.
This is a QR factorization of a complex matrix.
minGRU (Feng et al.) in PyTorch, plus a measured ladder of state-tracking recoveries — signed, rotation, Givens, and delta (DeltaNet-style Householder products) mixers with time decay, all under one parallel scan — with fused Triton GPU kernels as an optional backend
This repository contains the python implementation of various functions used in ML such as PCA and Linear Regression
LAPACK routine to apply a real elementary reflector `H = I - tau * v * v^T` to a real M by N matrix `C`.
To associate your repository with the householder topic, visit your repo's landing page and select "manage topics."