Introduction to Generative Modeling Using Quantum Machine Learning


Ever wondered how quantum computers work, and how they do machine learning? With quantum computing technologies nearing the ear of commercialization and quantum advantage, machine learning has been proposed as one of the most promising applications. One of the areas in which quantum computing is showing great potential is in generative models in unsupervised and semi-supervised learning.
In this training, you will develop a basic understanding of quantum computing and how it can be used in machine learning models, with special emphasis on generative models. We will focus on a particular architecture, the quantum circuit Born machine (QCBM), and use it to generate a simple dataset of bars and stripes.
No previous knowledge of quantum computing and the generative model is needed for this workshop.

Session Outline
Module 1: Generative Machine Learning
A brief overview of machine learning and generative machine learning, including the notions of generative adversarial networks and how they are used to generate realistic images.

Module 2: Quantum Computing
An introduction to what is quantum computing, including the notions of a qubit, Bloch sphere, quantum gates, quantum measurement, and entanglement.

Module 3: Quantum Generative Models
In this module, we learn how to build a quantum circuit and use it to build generative models. We’ll study the quantum circuit Born machine (QCBM) in more detail. Then we’ll code one in a Jupyter notebook using a quantum machine learning package. Finally, there will be a demo of Orquestra, a platform for writing and deploying code in quantum computers.

Background Knowledge
Background in machine learning and in programming and familiarity with Jupyter notebooks.
No knowledge of quantum computing or generative models required as we will be developing this knowledge as needed, but some foundational math knowledge such as matrix arithmetic, linear algebra, and probability is recommended.


Luis Serrano is a Quantum AI Research Scientist at Zapata Computing. He is the author of the book Grokking Machine Learning and maintains a popular YouTube channel where he explains machine learning in pedestrian terms.
Luis has previously worked in machine learning at Apple and Google, and at Udacity as the head of content for AI and data science. He has a PhD in mathematics from the University of Michigan, a master's and bachelors from the University of Waterloo, and worked as a postdoctoral researcher in mathematics at the University of Quebec at Montreal.