Build Quantum ML Models on Real Datasets
‼️Early-Bird Campaign Till July 31: General 50% off (code EB). Low-income countries 70% off (code Dev).
If you understand training loops, kernels, and neural networks, you already know most of what quantum machine learning requires. The concepts map directly: the kernel trick becomes quantum kernels, training loops become variational circuits, combinatorial optimization becomes QAOA. What's missing is the quantum layer — and that is precisely what this course teaches.
What is included:
⭐ 8 live sessions with recordings — theoretical foundations plus guided walkthroughs of the code files, so you see every implementation built line by line
⭐ 20+ Jupyter notebooks — complete, end-to-end QML pipelines in Qiskit 2.4, built on real datasets: leukemia, breast cancer, iris, and financial data
⭐ All PDF slides — complete derivations and written to be a standalone reference
⭐ A bank of R&D ideas in QML — starting points for research and projects
⭐ Includes Quantum Portfolio Optimization Workshop
🏢 Employer-sponsored: Most learners get reimbursed. Reimbursement request template available on request. A certificate of completion will be issued to all enrolled participants.
What you’ll learn
You will implement Quantum SVMs, Quantum neural networks, QAOA, Quantum k-means, and hybrid quantum-classical models in Qiskit 2.4.
States, gates, and measurement taught as linear algebra you already use
Superposition, interference, and entanglement as computational resources
Qiskit 2.4 primitives: SamplerV2 and EstimatorV2 from day one
Basis, amplitude, and angle encoding — and when to use each
Design quantum feature maps as feature engineering
Understand how encoding choices drive model expressivity
The kernel trick, extended to quantum Hilbert spaces
Train QSVMs on leukemia, breast cancer, and iris data
Benchmark quantum kernels honestly against classical baselines
Variational circuits as the quantum analogue of training loops
Choose ansätze, cost functions, and optimizers that actually converge
Diagnose barren plateaus and other trainability failures
Formulate Max-Cut and portfolio problems as QUBOs for QAOA
Implement quantum k-means for unsupervised learning
Apply QAOA to real financial data
Learn directly from Muhammad
Dr. Muhammad Faryad
Tier-2 IBM Qiskit Advocate, Qiskit 2.x Certified Developer
Who this course is for
AI/ML Engineers & Researchers — Who want to implement, benchmark, and evaluate quantum ML models with theoretical depth and practical codes.
Computational Scientists — Who want to expand their computational tools to include practical quantum computing routines for data analysis.
Tech Leads — Who want to develop insights for quantum ML use-cases, hardware limits, and quantum-ready workforce.
Prerequisites
Classical Machine Learning Concepts
This course assumes knowledge and fluency with basic classical ML concepts, including neural networks, supervised and unsupervised ML.
Working Knowledge of Numpy, Sklearn, Pandas
Students with prior experience in ML programming and familiar with Python tools will find the course most useful.
Familiarity with Matrices
Working experience with matrices is required. Exposure to linear algebra before the course will help you dig deeper.
What's included
Live sessions
Learn directly from Dr. Muhammad Faryad in a real-time, interactive format.
Video Recordings
All live sessions will be recorded and made available to students right after each session.
End-to-end code files
All code files used during the live sessions will be delivered to students before showing end-to-end model building for real datasets.
Lecture slides
All lecture slides used during live sessions will be provided to students before each session.
Dedicated Q/A sessions
Live questions/answers sessions and discussion on QML and converting your ML projects to QML projects
Solved Assignments
Theory/coding problems with solutions
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
8 live sessions • 40 lessons
Week 1
Sep
22
Lesson 1. The linear algebra you already use, written in quantum notation — states, gates, Bra-Ket language, Hilbert spaces, and your first circuit in Qiskit 2.4
Sep
24
Lesson 2. The three computational resources classical ML doesn't have — superposition, interference, and entanglement, with the Qiskit SamplerV2 primitive
Slides
Jupyter Notebooks
Practice Assignment with Solutions
Quantum Algorithms Notes
Accessing IBM Hardware
Week 2
Sep
29
Lesson 3. How a quantum circuit produces a prediction — observables & expectation values with Qiskit EstimatorV2 primitive and transition to Quantum ML
Oct
1
Lesson 4. Feature engineering for quantum models — data encoding strategies and quantum feature maps from data space to exponentially big Hilbert spaces
Slides
Jupyter Notebooks
Free resources
Schedule
Live sessions
3-4 hrs / week
See the syllabus for the detailed schedule.
Tue, Sep 22
4:00 PM—5:15 PM (UTC)
Thu, Sep 24
4:00 PM—5:15 PM (UTC)
Tue, Sep 29
4:00 PM—5:15 PM (UTC)
Playing with Qiskit code files
2-3 hrs / week
You will get the most out of the course if you spend time playing with the Qiskit code files explained during the live lessons.
Reviewing lesson slides
1-2 hrs / week
You should spend time reviewing the lesson slides before and after each live session since the slides have a rigorous treatment of QML theory.
Who has taken this course so far?
1. Lecturer, Northern Border University, Saudi Arabia
2. Research Assistant, Binghamton University, New York, USA
3. AVP Retail & Projects, Valiram Group, Malaysia
4. PhD Student, Queen’s University, Ontario, Canada
5. Software Engineer, Innovate for Consulting and Technology, Cairo, Egypt
6. Student, IISERM, Mohali, India
7. QC coordinator, Amerisci, New York, USA
8. Staff Machine Learning Engineer, Chewy, Florida, USA
9. Student, Universidad Anáhuac México Norte, México
10. Institut de Mathématiques et de Sciences Physiques, Bénin
11. Actuary, Sompo Insurance, México
12. Associate Professors, LUMS, QAU, Pakistan
13. Student, LUMS, Pakistan
14. Freelance Software Developers, UK, France
15. Post Doc, Saint Louis University, USA
16. Student, Canakkale Onsekiz Mart University, Turkey
17. Lecturer, Aston University, UK
18. Faculty, University Ibn Zohr, Morocco
19. Founder, Quantum Computing Company, USA
20. Research Assistant, Quantum Computing Company, South Korea
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$799
USD