When does class start/end?
Class hours may vary, please reach out to contact@ascendientlearning.com if you have any questions.
Advanced Quantum Machine Learning with Qiskit
This Quantum course teaches technical practitioners how to build, train, and deploy Quantum Machine Learning (QML) models using advanced Qiskit toolkits. Learners construct parameterized 2x2 quantum...
Read More
Duration
2 days
Course Code
QNTM-201
Available Formats
Classroom
Overview
Course Description
This Quantum course teaches technical practitioners how to build, train, and deploy Quantum Machine Learning (QML) models using advanced Qiskit toolkits. Learners construct parameterized 2x2 quantum blocks using the Cayley Transform, a mapping technique that guarantees strict unitarity during gradient descent so that trained circuits remain physically valid. The curriculum applies Simultaneous Perturbation Stochastic Approximation (SPSA) to train circuits on classical GPUs before deploying them to simulated noisy hardware, and addresses the two central scaling constraints practitioners encounter in the field: the memory limits of classical simulators and the qubit limits of near-term hardware. Participants implement circuit cutting, classical stitching using Quasi-Probability Decomposition (QPD), and Matrix Product State tensor networks to work around both constraints. The course culminates in execution on actual IBM Quantum hardware, where participants apply Zero Noise Extrapolation (ZNE) to recover signal accuracy lost to hardware noise.
Throughout, the course emphasizes practical, near-term applications relevant to fraud detection and anomaly detection, including use cases applicable to federal financial-integrity programs such as improper-payment and claims-fraud detection. As agencies build the quantum-literate technical staff called for under quantum-readiness workforce planning, this course provides hands-on grounding in how quantum circuits are trained, scaled, and executed under real hardware noise conditions, rather than a conceptual survey.
Skills Gained
By the end of this course, participants will be able to:
- Construct parameterized 2x2 quantum blocks using the Cayley Transform to ensure strict unitarity during model training.
- Train Quantum Machine Learning circuits using SPSA optimization and classical backpropagation on local GPUs.
- Implement circuit cutting and classical stitching using Quasi-Probability Decomposition (QPD) to execute large circuits on limited hardware.
- Apply Zero Noise Extrapolation (ZNE) to mitigate hardware noise during quantum inference.
- Deploy trained quantum circuits to IBM Quantum hardware to solve pattern recognition tasks, such as image classification and fraud detection.
Who Can Benefit
This course is designed for:
- Software engineers and data scientists who have completed foundational quantum computing training.
- AI/ML practitioners looking to implement quantum architectures for complex pattern recognition.
- Federal agency technical staff and contractors applying QML to fraud-detection and anomaly-detection use cases.
Prerequisites
Participants should enter this course with:
- Completion of the Quantum Computing Foundations course (or equivalent foundational quantum knowledge).
- Proficiency in Python and familiarity with standard machine learning concepts.
- Basic understanding of PyTorch or TensorFlow workflows.
Organizational Objectives
This course assists organizations to:
- Build scalable QML pipelines that bypass classical memory limits using tensor networks and circuit cutting.
- Enable anomaly detection and pattern recognition capabilities for federal and enterprise clients using near-term quantum hardware.
- Reduce AI model training costs by equipping teams with quantum architectures that use exponentially fewer parameters while maintaining mathematical stability.
- Establish a bench of practitioners capable of executing complex quantum circuits on noisy hardware using advanced mitigation techniques.
- Build quantum-literate technical teams capable of applying QML architectures to fraud-detection and anomaly-detection use cases as agencies and enterprises expand quantum-readiness initiatives beyond cryptography alone.
Software
All participants require a laptop or desktop computer with a modern web browser and broadband internet.
Course Details
Course Details
Module 1 – Parameterization and the Cayley Transform
By the end of this module, you will be able to design fully trainable quantum circuits using the Cayley Transform. You will also be able to explain how mapping real numbers to complex unitary matrices guarantees physical legality during gradient descent.
- The limitations of standard quantum gates in machine learning
- Constructing 2x2 Hermitian matrices using real parameters
- Applying the Cayley Transform to generate strict unitary gates
- Building custom CayleySingleQubitGate and CayleyTwoQubitGate classes in Qiskit
- Hands-on Lab: Define the Cayley Transform logic in Python and integrate custom parameterized gates into a Qiskit quantum circuit.
Module 2 – Circuit Training and SPSA Optimization
By the end of this module, you will be able to train parameterized quantum circuits using SPSA optimization on a local simulator. You will also be able to map continuous expectation values to discrete quantum measurements for ML loss functions.
- The division of labor: Aer Simulator (engine) vs. SPSA (brain)
- Mapping data labels to quantum expectation values
- Estimating gradients using Simultaneous Perturbation Stochastic Approximation (SPSA)
- Executing training loops on local CPUs/GPUs using Qiskit Aer
- Hands-on Lab: Build a 9-qubit image recognizer using Cayley blocks and train it locally using SPSA to distinguish vertical and horizontal lines.
Module 3 – Scaling with Tensor Networks and Tournament Trees
By the end of this module, you will be able to scale quantum circuit simulations beyond standard memory limits using Matrix Product States (MPS). You will also be able to design shallow circuit topologies to reduce depth and mitigate barren plateaus.
- The memory wall: exponential memory scaling in statevectors
- Using Matrix Product States (MPS) for linear memory scaling
- Designing Tournament Tree topologies for logarithmic depth
- Preventing overfitting in expressive quantum circuits using L2 regularization
- Hands-on Lab: Modify the linear chain topology to a Tournament Tree and retrain the circuit using the MPS simulator to observe memory efficiency.
Module 4 – Circuit Cutting and Classical Stitching
By the end of this module, you will be able to execute large quantum circuits on limited hardware by cutting the circuit into smaller fragments. You will also be able to reconstruct the global expectation value using Quasi-Probability Decomposition (QPD).
- The hardware wall: running 10-qubit circuits on 5-qubit machines
- Quasi-Probability Decomposition (QPD) math for CNOT gates
- Using IBM's qiskit-addon-cutting to physically slice circuits
- Classical stitching and the sampling overhead (variance explosion)
- Hands-on Lab: Physically cut a 10-qubit trained circuit into two 5-qubit fragments, execute them independently, and mathematically stitch the results back together.
Module 5 – Hardware Execution and Noise Mitigation
By the end of this module, you will be able to deploy classically trained quantum circuits to real IBM Quantum hardware. You will also be able to apply Zero Noise Extrapolation (ZNE) to recover accuracy lost to hardware noise.
- The noise floor and NISQ limitations
- Transpiling abstract circuits to physical basis gates
- Manual Zero Noise Extrapolation (ZNE): folding circuits to amplify noise
- Integrating ZNE with cut circuit fragments for final inference
- Hands-on Lab: Run the cut and stitched image recognizer on a simulated noisy backend, apply ZNE to the fragments, and plot the mitigated results against the ideal output.
Schedule
FAQ
Does the course schedule include a Lunchbreak?
Classes typically include a 1-hour lunch break around midday. However, the exact break times and duration can vary depending on the specific class. Your instructor will provide detailed information at the start of the course.
What languages are used to deliver training?
Most courses are conducted in English, unless otherwise specified. Some courses will have the word "FRENCH" marked in red beside the scheduled date(s) indicating the language of instruction.
What does GTR stand for?
GTR stands for Guaranteed to Run; if you see a course with this status, it means this event is confirmed to run. View our GTR page to see our full list of Guaranteed to Run courses.
How do I find an Ascendient Learning training location?
We have training locations across the United States and Canada - View a complete list of classroom training locations.
Which delivery formats are available?
At Ascendient Learning, we offer training that is Instructor-Led, Online, Virtual, and Self-Paced.
Does Ascendient Learning deliver group training?
Yes, we provide training for groups, individuals and private on sites. View our group training page for more information.
What does vendor-authorized training mean?
As a vendor-authorized training partner, we offer a curriculum that our partners have vetted. We use the same course materials and facilitate the same labs as our vendor-delivered training. These courses are considered the gold standard and, as such, are priced accordingly.
Is the training too basic, or will you go deep into technology?
It depends on your requirements, your role in your company, and your depth of knowledge. The good news about many of our learning paths, you can start from the fundamentals to highly specialized training.
How up-to-date are your courses and support materials?
We continuously work with our vendors to evaluate and refresh course material to reflect the latest training courses and best practices.
Are your instructors seasoned trainers who have deep knowledge of the training topic?
Ascendient Learning instructors have an average of 27 years of practical IT experience and have also served as consultants for an average of 15 years. To stay current, instructors spend at least 25 percent of their time learning new, emerging technologies and courses.
Do you provide hands-on training and exercises in an actual lab environment?
Lab access is dependent on the vendor and the type of training you sign up for. However, many of our top vendors will provide lab access to students to test and practice. The course description will specify lab access.
Will you customize the training for our company’s specific needs and goals?
We will work with you to identify training needs and areas of growth. We offer a variety of training methods, such as private group training, on-site of your choice, and virtually. We provide courses and certifications that are aligned with your business goals.
How do I get started with certification?
Getting started on a certification pathway depends on your goals and the vendor you choose to get certified in. Many vendors offer entry-level IT certification to advanced IT certification that can boost your career. To get access to certification vouchers and discounts, please contact info@ascendientlearning.com.
Will I get access to content after I complete a course?
You will get access to the PDF of course books and guides, but access to the recording and slides will depend on the vendor and type of training you receive.
How do I request a W9 for Ascendient Learning?
View our filing status and how to request a W9.
Reviews
I was very satisfied about how the course was organized. Sean Did a very good work
Thank Tech Data for sponsoring this course you really take care of your partners.
The platform is very intuitive and easy to navigate. Great tool for learning
The instructor was thorough and they also provided hands-on demonstrations with labs.
The exit certified aws course provided a good introduction to the tools available on aws.
