Tensor-based algorithms for image classification

10/04/2019
by   Stefan Klus, et al.
31

The interest in machine learning with tensor networks has been growing rapidly in recent years. The goal is to exploit tensor-structured basis functions in order to generate exponentially large feature spaces which are then used for supervised learning. We will propose two different tensor approaches for quantum-inspired machine learning. One is a kernel-based reformulation of the previously introduced MANDy, the other an alternating ridge regression in the tensor-train format. We will apply both methods to the MNIST and fashion MNIST data set and compare the results with state-of-the-art neural network-based classifiers.

READ FULL TEXT

page 1

page 10

page 13

page 14

05/18/2016

Supervised Learning with Quantum-Inspired Tensor Networks

Tensor networks are efficient representations of high-dimensional tensor...
07/06/2022

Tensor networks in machine learning

A tensor network is a type of decomposition used to express and approxim...
03/26/2019

Generative Tensor Network Classification Model for Supervised Machine Learning

Tensor network (TN) has recently triggered extensive interests in develo...
09/16/2022

Deep tensor networks with matrix product operators

We introduce deep tensor networks, which are exponentially wide neural n...
06/07/2019

TensorNetwork for Machine Learning

We demonstrate the use of tensor networks for image classification with ...
12/31/2017

Learning Relevant Features of Data with Multi-scale Tensor Networks

Inspired by coarse-graining approaches used in physics, we show how simi...
05/15/2019

Number-State Preserving Tensor Networks as Classifiers for Supervised Learning

We propose a restricted class of tensor network state, built from number...