A continuous analogue of the tensor-train decomposition
Sign Up to like & getrecommendations! Published in 2019 at "Computer Methods in Applied Mechanics and Engineering"
DOI: 10.1016/j.cma.2018.12.015
Abstract: We describe a new function approximation framework based on a continuous extension of the tensor-train decomposition. The approximation, termed a function-train (FT), results in a tensor-train structure whose cores are univariate functions. An advantage of… read more here.
Keywords: tensor train; approximation; train decomposition;
TT-MLP: Tensor Train Decomposition on Deep MLPs
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3240784
Abstract: Deep multilayer perceptrons (MLPs) have achieved promising performance on computer vision tasks. Deep MLPs consist solely of fully-connected layers as the conventional MLPs do but adopt more sophisticated network architectures based on mixer layers composed… read more here.
Keywords: tensor train; train decomposition; deep mlps; train ... See more keywords
TT-CIM: Tensor Train Decomposition for Neural Network in RRAM-Based Compute-in-Memory Systems
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Circuits and Systems I: Regular Papers"
DOI: 10.1109/tcsi.2023.3344550
Abstract: Compute-in-Memory (CIM) implemented with Resistive-Random-Access-Memory (RRAM) crossbars is a promising approach for accelerating Convolutional Neural Network (CNN) computations. The growing size in the number of parameters in state-of-the-art CNN models, however, creates challenge for on-chip… read more here.
Keywords: tensor train; memory; rram; train decomposition ... See more keywords