Quantum Machine Learning Workshop
11-12.04.2026

Quantum Machine Learning (QML) is a discipline seeking to take advantage of quantum mechanical processes to induce or enhance machine learning. It combines in novel ways the concepts and algorithms adopted from Quantum Computing and Machine Learning, and is underpinned by the Quantum Mechanics theory and formalism.

This workshop provides an introduction to Quantum Machine Learning using PennyLane and PyTorch, with hands-on exercises and take-home challenges. The workshop includes four practical sessions that cover the QML concepts, models, and techniques. The sessions explore the development of quantum estimators and classifiers, their training with various optimisers, loss and cost functions, as well as model testing and scoring using variety of metrics. It finally, explains how to create hybrid quantum-classical QML models.

Key information

• Workshop dates: 11-12.04.2026 (2 days)

• Organizers: QPoland & Fundacja Quantum AI

• Duration of classes each day: from 10:00 AM  to 2:00 PM (UTC+2)

• Online meeting platform: Zoom

• Communication platform: Discord

• Instructor: Jacob Cybulski 

• Mentors: Tomasz Rybotycki, Sebastian Zając, Paweł Gora

• Who can attend? The event is only for people who are above 18 years old. It is also mandatory to register and be invited. We also highly recommend checking the "Prerequisite Knowledge" section.

• Registration form (will be open until 10.04.2026, EoD UTC+2): https://forms.gle/UV86KDRdTXbYgyzv9 

• Certification: You can get a certificate if you take an online quiz based on the work covered by the workshop activities and complete it successfully within 1 week of the event. 

Anticipated schedule

Note:  All demos can be followed with hands-on code walkthroughs and support from mentors on Discord.

         All challenges have been designed as self-directed study activities outside the workshop.

Workshop Day 1 (4 hours) / 1 instructor and mentors

• Welcome: Introduction, plan for day 1 and rules of engagement (10 mins)

• Session 1: Introduction to QML (30 mins)

• Session 2: QML foundation (80 mins)

◦     Presentation: QML concepts, models, and techniques (30 mins)

◦     Demo: PennyLane basics, simple models, experiments in model improvement (40 mins)

◦     Homework: Create a simple model, with local/global cost (5 mins explanation)

◦     Challenge: Writing own optimiser and/or loss function (5 mins explanation)

• Coffee Break (30 mins)

• Session 3: QNN estimator development (80 mins)

◦     Presentation: Quantum models, gradients, loss / cost, optimisers and diagnostics (30 mins)

◦     Demo: QNN estimator in PennyLane, training and test scoring (40 mins)

◦     Homework: Create, train and score a model for a complex data set (5 mins explanation)

◦     Challenge: Create a reuploading estimator (5 mins explanation)

• Summary: Reflection and day 2 preview (10 mins)

Workshop Day 2 (4 hours) / 1 instructor and mentors

• Summary: Reflection and plan for day 2 (10 mins)

• Session 4: Intermediate QML (90 mins)

◦     Presentation: Quantum classifiers, metrics, model training and testing (40 mins)

◦     Demo: PennyLane classifier in PennyLane with PyTorch (40 mins)

◦     Homework: Create and improve a quantum classifier (5 mins explanation)

◦     Challenge: Create a multinomial classifier (5 mins explanation)

• Coffee Break (30 mins)

• Session 5: Advanced QML (90 mins)

◦     Presentation: Hybrid quantum-classical autoencoders (40 mins)

◦     Demo: Hybrid autoencoders in PennyLane with PyTorch (40 mins)

◦     Homework: Create and improve a hybrid autoencoder (5 mins explanation)

◦     Challenge: Develop and test a denoising quantum autoencoder (5 mins explanation)

• Summary: Summary, reflection and the next steps (20 mins)

Prerequisite Knowledge

• Python 3

◦     Familiarity with: venv or anaconda (virtual environments)

◦     Intermediate Python with some advanced concepts, e.g. classes

◦     Knowledge of packages: numpy, pandas, scikit-learn, matplotlib, jupyter

◦     Knowledge of pytorch and gradients would greatly help

• Quantum Computing

◦     Fundamentals: qubits, circuits, gates, quantum state, measurement, Dirac notation

◦     Maths: complex numbers, matrices / tensors, some statistics and probability theory

◦     Hands on: one of the QC platforms (Qiskit, PennyLane, Cirq, …)

• Classical Machine Learning

◦     Models: classification, regression, neural networks

◦     Model training: optimisers, loss / cost function, gradients

◦     Model performance: measurements, training vs testing

• Workshop communication platforms

◦     Discord (notes, networking, discussions, get help and pointers)

◦     GitHub (demos, exercises and data)

◦     Pre-reading of presentations for Day 1 and Day 2

Pre-Workshop preparation (use own computer with recent Linux / Window / macOS)

• Download all resources (notes, code and data)

• Install the recommended Python virtual environment (venv + requirements)

• Undertake some preliminary exercises and get familiar with:

◦     PyTorch, tensors, gradients and neural networks:
AssemblyAI, “PyTorch Crash Course - Getting Started with Deep Learning”, Jul 2022.
https://www.youtube.com/watch?v=OIenNRt2bjg (50 mins)

◦     PennyLane, functions, circuits, qnodes and measurements:
Diego Emilio Serrano, “Basic Introduction to PennyLane”, Feb 2023.
https://www.youtube.com/watch?v=MCDHAn-GvA8 (40 mins)

◦     PennyLane circuit creation and execution for busy people:
Isaac De Vlugt, “My first quantum circuit in PennyLane”, Sept 2023
https://www.youtube.com/watch?v=uCm027_jvZ0 (5 mins)

Workshop software environment (installation instructions and requirements file will be provided)

• Create a virtual environment created with venv or anaconda for Python 3.11 and pip 25.0+

• Detailed instructions on how to install all workshop software will be provided on GitHub

Organizers