Quantum Machine Learning

With IBM QiskitTM

First-year Innovation & Research Experience (FIRE) at the University of Maryland, College Park


What is Quantum Machine Learning?

Quantum Machine Learning (QML) is a research stream starting Fall 2022 as a part of the FIRE program at the University of Maryland, College Park under the Technology & Applied Science cluster. Several existing courses at UMD cover the distinct fields of machine learning (ML) and quantum computing (QC) independently, but the QML research stream will be the first one at the university to introduce students to a burgeoning new space that is currently developing at the intersection of these fields: quantum machine learning.

The concept of performing ML on quantum computers has long been a goal of computer scientists from both specialties, and bleeding-edge new cloud quantum computing technology like the IBM QiskitTM which we use in this course has finally provided the bridge between that dream and reality. The QML stream is your opportunity as a student to get ahead-of-the-curve access and insight into this exciting new technology and to get a chance to engage in hands-on exploration of one of the most fascinating and dynamic new fields of science today.

How is the stream structured?

QML is a year-long, comprehensive, research experience intended for first-year students.

Spring Semester: This is the first semester in the sequence. Students will spend their first 3-4 weeks creating strong foundational understanding of fundamentals of data science, quantum mechanics, and machine learning, including principles of artificial intelligence, deep learning, classification/regression problems. Rest of the semester we use these concepts and the state-of-the-art tools and techniques to analyze Big Data sourced directly either from detectors recording high-energy proton-proton collisions at the Large Hadron Collider (LHC) at CERN in Geneva or particle data collected by underground experiments, originating from astrophysical sources such as supernovas, gamma ray bursts, and black holes. During this semester you will also get access to one of the Worldwide LHC Computing Grid, WLCG Tier 3 centers owned by the HEP group in the UMD Physics Department.

Fall Semester: This is the second semester in the sequence. We will spend initial few weeks on the concepts and a brief history of quantum computing, theoretical explanation of qubit, and speculated impacts of QC over classical computers in fields such as cryptography and optimization, discussion and brief exercises intended to foster basic familiarity with both common machine learning toolkits (sci-kit learn, tensorflow) and our course's quantum computing tool provider, IBM QiskitTM. The remainder of the time will focus on proposing and completing independent projects based on the principles you have learned in the course, either alone or in a small group of students.

How can I join? What can I expect?

If you're a student interested in exploring quantum machine learning further, we would be happy to have you join the program! If you're an incoming freshman at the university, you may apply to be admitted to the First-year Innovation & Research Experience (FIRE) program here. Once admitted, you will enroll in the general-purpose first semester course FIRE120, and afterwards will have the opportunity to enroll in our FIRE198 & FIRE298 course sequence during the subsequent Spring and Fall.

QML only requires 1 hour of class time per week, but research students are expected to spend additional time for discussions, project work, and collaborative activities during the week as well. For the introductory portion of the course, students will complete a series of brief activities intended to familiarize them with fundamentals of data analysis, and staple machine learning tasks such as clustering and regression. Later we work on similar activities but with IBM QiskitTM and the with quantum circuits rather than conventional neural networks.

During the latter part of the course, students will work with peer research mentors and their classmates in small groups to propose a plan for designing and implementing an independent quantum machine learning project using the skills they have learned in the previous weeks. This proposal will undergo revision and approval by the professor, and students will then be given guided research time to collaborate, discuss, plan, and ultimately realize their proposals. Students will ultimately have an opportunity to present their completed projects at the FIRE Summit in November as well as other events showcasing undergrad research at UMD.


The purpose of the QML journal Curiosity is to showcase the research work done by the undergrad students during the year-long experience as part of the Quantum Machine Learning stream.

Course Materials

Whether you're an incoming QML research student, a student considering joining the stream, or just someone interested in QML, we will be excited to provide you with our course material and code packaged as Jupyter notebooks. QML students spend 4-6 weeks completing these notebooks and learning the fundamentals of quantum and machine learning principles before beginning their personal projects.

Our People


Dr. Shabnam Jabeen

Research Peer Leaders

Meer Abdullah

Scott Chen

Karen Rezkalla

Matt Panayos

Chris Song

Ze'ev Vladimir

Colin Bright

Saniya Nazeer

Naaman Trumbull

Benjamin-Nicolas Enwesi

Rohit Kommuru

Past Research Student Outcomes

Dr. Jabeen has taught research courses and mentored a large number of research students during her time at the University of Maryland, College Park. Many of those students have gone on to gradute studies at:

or work at: