AutoQML: Automatic Generation and Training of Robust Quantum-Inspired Classifiers by Using Genetic Algorithms on Grayscale Images

08/28/2022
by   Sergio Altares López, et al.
CSIC
4

We propose a new hybrid system for automatically generating and training quantum-inspired classifiers on grayscale images by using multiobjective genetic algorithms. We define a dynamic fitness function to obtain the smallest possible circuit and highest accuracy on unseen data, ensuring that the proposed technique is generalizable and robust. We minimize the complexity of the generated circuits in terms of the number of entanglement gates by penalizing their appearance. We reduce the size of the images with two dimensionality reduction approaches: principal component analysis (PCA), which is encoded in the individual for optimization purpose, and a small convolutional autoencoder (CAE). These two methods are compared with one another and with a classical nonlinear approach to understand their behaviors and to ensure that the classification ability is due to the quantum circuit and not the preprocessing technique used for dimensionality reduction.

READ FULL TEXT

page 1

page 5

page 7

page 10

page 11

05/26/2021

Automatic design of quantum feature maps

We propose a new technique for the automatic generation of optimal ad-ho...
02/04/2021

An end-to-end trainable hybrid classical-quantum classifier

We introduce a hybrid model combining a quantum-inspired tensor network ...
04/19/2021

Quantum Algorithms for Data Representation and Analysis

We narrow the gap between previous literature on quantum linear algebra ...
05/23/2022

PCA-Boosted Autoencoders for Nonlinear Dimensionality Reduction in Low Data Regimes

Autoencoders (AE) provide a useful method for nonlinear dimensionality r...
02/24/2021

Entanglement Diagnostics for Efficient Quantum Computation

We consider information spreading measures in randomly initialized varia...

Please sign up or login with your details

Forgot password? Click here to reset