Unsupervised Recognition of Informative Features via Tensor Network Machine Learning and Quantum Entanglement Variations

TL;DR

This paper introduces an unsupervised feature recognition method using tensor networks and quantum entanglement, identifying critical features in images by analyzing entanglement entropy variations.

Contribution

It proposes a novel unsupervised scheme that leverages entanglement entropy variations in tensor networks to recognize informative features without labels.

Findings

Successfully applied to toy and real datasets including MNIST and brain images.

Demonstrates that entanglement entropy variations highlight critical features.

Reveals entanglement structures among features in image data.

Abstract

Given an image of a white shoe drawn on a blackboard, how are the white pixels deemed (say by human minds) to be informative for recognizing the shoe without any labeling information on the pixels? Here we investigate such a ``white shoe'' recognition problem from the perspective of tensor network (TN) machine learning and quantum entanglement. Utilizing a generative TN that captures the probability distribution of the features as quantum amplitudes, we propose an unsupervised recognition scheme of informative features with the variations of entanglement entropy (EE) caused by designed measurements. In this way, a given sample, where the values of its features are statistically meaningless, is mapped to the variations of EE that statistically characterize the gain of information. We show that the EE variations identify the features that are critical to recognize this specific sample, and the EE itself reveals the information distribution of the probabilities represented by the TN model. The signs of the variations further reveal the entanglement structures among the features. We test the validity of our scheme on a toy dataset of strip images, the MNIST dataset of hand-drawn digits, the fashion-MNIST dataset of the pictures of fashion articles, and the images of brain cells. Our scheme opens the avenue to the quantum-inspired and interpreted unsupervised learning, which can be applied to, e.g., image segmentation and object detection.