Work

Learning relevant features of data with multi-scale tensor networks

Year: 2018
Type: article
Abstract: Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of features nevertheless able to give good performance.
Author: E Miles Stoudenmire
Institution: Flatiron Institute
Language: English
Open Access status: green
OpenAlex ID: W2782213776
FWCI: 8.405
Cites: 77
Cited by: 200
Related to: 9