Development of Quantum Autoencoders

Authors:
Jacob L. Cybulski, Enquanted, Melbourne, Australia
jacobcybulski....
Sebastian Zając, SGH Warsaw School of Economics, Warsaw, Poland sebastianzajac...
Abstract:
This presentation describes development aspects of variational quantum autoencoders. As an example, we will discuss the “worst case” scenario of a quantum autoencoder used in denoising time-series and signals.
The talk highlights the quantum model’s architectural choices, data encoding strategies, ansatz structures and their parameterisation, circuit measurement alternatives and the interpretation of measurement results. Practical issues in training such models will also be covered, to include the selection of an optimiser and its loss function, as well as the execution of a quantum model on simulators, GPU accelerators and QPUs. Methods of model testing will also be explained.
Speaker:
Jacob Cybulski is the founder of Enquanted, providing research, training and consulting services in the area of quantum computing and quantum machine learning. Jacob’s projects involve developing quantum machine learning solutions for prediction, forecasting and anomaly detection, as well as, investigation of business and scientific applications of quantum computing. He is dedicated to teaching and promotion of quantum technology. Jacob’s professional activities also include work in classical machine learning, business analytics and data visualisation. In the past, Jacob conducted research at Deakin University, University of Melbourne, La Trobe University and RMIT University, in Melbourne, Australia.
Moderator: Dr. Sebastian Zajac, member of QPoland