Pinned Repositories
ConvPCA
A PCA for time series. Related to PCA in the frequency domain, spectral PCA or dynamic PCA. But formulated in the time domain.
EnhancedPHAT
A simple method for correcting the phase bias suffered by GCC
Filterbank
Filterbank in Tensorflow and Pytorch
FilterbanksBestPractices
Tips for best practices with filterbanks
IVA4Cocktail
Neural network density models for speech separation.
MCMIL
A multiclass multiple instance learning method. Only need to know whether any instance of a class exists or not in a sample. Demonstration on multiple object detection and localization.
psgd_np
Numpy implementation of preconditioned stochastic gradient descent
psgd_tf
Tensorflow implementation of preconditioned stochastic gradient descent
psgd_torch
Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditioner and more)
TriNet4PdfEst
Triangular neural network (network with triangular block matrices as weights) for density estimation and data generation.
lixilinx's Repositories
lixilinx/psgd_torch
Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditioner and more)
lixilinx/FilterbanksBestPractices
Tips for best practices with filterbanks
lixilinx/psgd_tf
Tensorflow implementation of preconditioned stochastic gradient descent
lixilinx/IVA4Cocktail
Neural network density models for speech separation.
lixilinx/EnhancedPHAT
A simple method for correcting the phase bias suffered by GCC
lixilinx/Filterbank
Filterbank in Tensorflow and Pytorch
lixilinx/MCMIL
A multiclass multiple instance learning method. Only need to know whether any instance of a class exists or not in a sample. Demonstration on multiple object detection and localization.
lixilinx/TriNet4PdfEst
Triangular neural network (network with triangular block matrices as weights) for density estimation and data generation.
lixilinx/psgd_np
Numpy implementation of preconditioned stochastic gradient descent
lixilinx/ConvPCA
A PCA for time series. Related to PCA in the frequency domain, spectral PCA or dynamic PCA. But formulated in the time domain.
lixilinx/Flexible_quantization
A simple formula supports eight types of quantization