Name: Kim Batselier
Type: User
Company: Delft University of Technology
Bio: Working on tensor methods for high-dimensional data and signal processing, nonlinear system identification, machine learning and control.
Location: Netherlands
Blog: https://sites.google.com/view/kim-batselier/home
Kim Batselier's Projects
The Julia Language: A fresh approach to technical computing.
Matlab Codes for Kernelized Support Tensor Train Machines (KSTTM)
Code for the tensor train Kalman filter applied to the LSSVM dual problem
Converts a tensor train into either a Tucker decomposition or into a MERA. The tensor train is 'unfolded' layer by layer into a MERA. The rank-lowering disentanglers in the MERA are obtained through an orthogonal Procrustes problem.
MIMO Volterra Modified Alternating Linear Scheme identification algorithms
Polynomial Numerical Linear Algebra package for Julia
MATLAB/OCTAVE functions for the Polynomial Numerical Linear Algebra Framework
Symmetric Tensor Eigen-Rank-One Iterative Decomposition
Code to reproduce results in the article ``Enforcing symmetry in tensor network MIMO Volterra identification"
Tensor Network B-splines and its application in nonlinear system identification
Tensor Kronecker Product Singular Value Decomposition
Extended Kalman filtering with low-rank Tensor Networks for MIMO Volterra system identification
Tensor Network Kalman filter
Tensor Network MOESP method for the identification of polynomial state space models
Tensor Network randomized SVD
Tensor Sum-product Networks
Fast and accurate tensor completion using tensor trains with a system identification approach
Tensor Train polynomial classifier
Tensor Train Rank-1 decomposition