Tensor network to learn the wavefunction of data

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dymarsky, Anatoly, Pavlenko, Kirill
Format: Preprint
Veröffentlicht: 2021
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909089514127360
author Dymarsky, Anatoly
Pavlenko, Kirill
author_facet Dymarsky, Anatoly
Pavlenko, Kirill
contents How many different ways are there to handwrite digit 3? To quantify this question imagine extending a dataset of handwritten digits MNIST by sampling additional images until they start repeating. We call the collection of all resulting images of digit 3 the "full set." To study the properties of the full set we introduce a tensor network architecture which simultaneously accomplishes both classification (discrimination) and sampling tasks. Qualitatively, our trained network represents the indicator function of the full set. It therefore can be used to characterize the data itself. We illustrate that by studying the full sets associated with the digits of MNIST. Using quantum mechanical interpretation of our network we characterize the full set by calculating its entanglement entropy. We also study its geometric properties such as mean Hamming distance, effective dimension, and size. The latter answers the question above -- the total number of black and white threes written MNIST style is $2^{72}$.
format Preprint
id arxiv_https___arxiv_org_abs_2111_08014
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Tensor network to learn the wavefunction of data
Dymarsky, Anatoly
Pavlenko, Kirill
Quantum Physics
Machine Learning
How many different ways are there to handwrite digit 3? To quantify this question imagine extending a dataset of handwritten digits MNIST by sampling additional images until they start repeating. We call the collection of all resulting images of digit 3 the "full set." To study the properties of the full set we introduce a tensor network architecture which simultaneously accomplishes both classification (discrimination) and sampling tasks. Qualitatively, our trained network represents the indicator function of the full set. It therefore can be used to characterize the data itself. We illustrate that by studying the full sets associated with the digits of MNIST. Using quantum mechanical interpretation of our network we characterize the full set by calculating its entanglement entropy. We also study its geometric properties such as mean Hamming distance, effective dimension, and size. The latter answers the question above -- the total number of black and white threes written MNIST style is $2^{72}$.
title Tensor network to learn the wavefunction of data
topic Quantum Physics
Machine Learning
url https://arxiv.org/abs/2111.08014