Staging environment
Workshop

Quantum Machine Learning Workshop

Muhammad Faryad

Quantum Machine Learning Scientist

Quantum ML in 4 Hours: Build Real QNNs & Kernels in Qiskit

Most ML engineers are hearing about quantum advantage—but have no practical way to evaluate or use it. This creates a real professional gap: you’re expected to understand quantum ML, yet most resources are either too theoretical or too fragmented to apply. This workshop solves that gap directly.

In just 4 hours, you’ll move from zero intuition to actually building and testing quantum models—quantum kernels, QSVMs, and QNNs—using Qiskit. You won’t just “learn concepts”; you’ll implement circuits, encode data into feature maps, and see how quantum models behave on real problems. All you need to start is the basics of quantum computing. If you are familiar with Qiskit and quantum computing, this workshop will take you to Quantum ML applications.

Why this matters now:

  • Quantum computing is transitioning from hype to early adoption—teams need practitioners, not observers.

  • Hiring managers increasingly value “applied exposure” to quantum tools.

  • Understanding when quantum models help (and when they don’t) is a competitive edge.

What you’ll learn

    Workshop agenda

    • Quantum ML Models

      What is QML? Hybrid quantum-classical workflow: Data → Feature Map → Variational Circuit → Measurement, Deterministic vs probabilistic models.

    • Foundations: Data Encoding / Feature Maps

      Basis, Amplitude, Angle, Phase, and Hamiltonian encoding. Expressivity intuition. Why is encoding the most critical in QML?

    • Hands-on #1 (Jupyter Notebook): Data Encoding

      Basis, amplitude, and angle encodings. Z, ZZ, Pauli feature maps, Two-local and N-local maps, Entanglement creation

    • Variational Quantum Circuits / Quantum Neural Networks

      Connection to classical linear models in feature space, Barren Plateaus.

    • Hands-on #2 (Jupyter Notebook): Build a VQC

      Data pre-processing, Rescaling, Feature map + ansatz, Train a binary classifier, Network depth vs accuracy.

    • Break

      15-minute break.

    • Quantum Kernels

      How do encoding schemes relate to the kernel? Why do kernels avoid trainability issues? Why do quantum kernels give an advantage over classical kernels?

    • Quantum Support Vector Machines

      Support vector machine model, why is quantum SVM better? Kernel alignment in QSVM.

    • Hands-on #3 (Jupyter Notebook): QSVM Implementation

      Build and train a QSVM on a practical dataset, compare with classical SVM, Engineer kernel to change training/test accuracies

    Learn directly from Muhammad

    Muhammad Faryad

    Muhammad Faryad

    Contact

    Quantum Machine Learning Scientist

    Penn State College of Engineering
    Qiskit
    Abdus Salam International Centre for Theoretical Physics
    LUMS
    See all products from Dr. Faryad

    Who this workshop is for

    • ML Engineers: Extend ML expertise into quantum kernels and quantum neural networks if you have basic quantum computing knowledge.

    • AI / ML Researchers: Reproduce, benchmark, and rigorously evaluate quantum ML models with solid theoretical depth.

    • Tech Lead / Founders: Develop insights for quantum machine learning, hardware limits, and credible quantum-ready use cases.

    Prerequisites

    • What basic knowledge is required to benifit from this workshop?

      The workshop assumes that participants have basic knowledge of quantum computing and now want to go deeper into quantum ML.

    • Is prior Qiskit programming experience required?

      No. But an understanding of basic gates and circuit language of quantum computing is required. We will not review quantum gates.

    • Is ML experience required?

      Yes, the workshop assumes that participants have an understanding of ML/AI concepts and want to transition to Quantum ML/AI.

    What's included

    Muhammad Faryad

    Live sessions

    Learn directly from Muhammad Faryad in a real-time, interactive format.

    Lifetime access

    Go back to the course content and recordings whenever you need to.

    Jupyter Notebooks

    Get access to and complete a walkthrough of the end-to-end quantum ML models on real datasets using Qiskit 2.3

    Lecture material

    Get access to lecture notes, slides, and solved exercises

    Certificate of completion

    Share your new skills with your employer or on LinkedIn.

    Maven Guarantee

    Your purchase is backed by the Maven Guarantee.

    Free resource

    Build your first quantum support vector machine cover image

    Build your first quantum support vector machine

    Quantum support vector machine model

    Understand the key similarities and differences between classical and quantum SVMs.

    Why quantum SVM can be better than classical SVM

    Learn how quantum SVMs access exponentially larger kernel spaces without added computational cost.

    Implement quantum SVM in Qiskit 2.3 on real dataset

    Code a quantum SVM in Qiskit 2.3 and apply it to binary classification of a leukemia dataset.

    Who has taken the QML course so far?

    1. Founder, Quantum Computing Company, USA

    2. Quantum Research Assistant, South Korea

    3. Freelance ML developer, France

    4. Physics Faculty Members, Pakistan, Morocco

    5. Cyber Security Lecturer, UK

    6. Graduate Students/Researchers, Pakistan, Turkey

    7. Post-Doc Fellow, USA

    Frequently asked questions

    Maven for Teams

    Reimbursement

    Get your company to pay

    Everything L&D needs: email template, receipts, and certificate of completion.

    Get reimbursed

    Private cohort

    Run a cohort for your org

    A dedicated cohort with a custom schedule and curriculum, tailored to your team.

    Book a private cohort