Planned
Quantum Machine Learning
Where quantum circuits meet machine learning, with honest limits. 43 planned courses across six levels.
All courses on this page are planned. Titles, order and durations may change before launch.
Foundation 1 planned
- QQ-402What Is Quantum Machine Learning?
Identify common forms of quantum machine learning and the role of a classical data pipeline.Foundation Planned
Beginner 2 planned
- QQ-401Machine Learning Refresher for Quantum
Review classification, regression, validation and generalisation concepts used in QML experiments.Beginner Planned - QQ-423Designing a First QML Experiment
Formulate a testable QML hypothesis and identify which observations could support or undermine it.Beginner Planned
Intermediate 18 planned
- QQ-403Quantum Data Encoding: Angle, Amplitude & Basis
Compare basis, angle and amplitude encodings based on feature dimension and state-preparation cost.Intermediate Planned - QQ-404Quantum Feature Maps
Connect a feature-map circuit to the state similarities it induces across input examples.Intermediate Planned - QQ-405Quantum Kernels & SVMs
Construct a kernel comparison and examine how a quantum kernel fits into a classical SVM workflow.Intermediate Planned - QQ-406Variational Quantum Classifiers
Explain how a parameterised circuit can produce class scores and how a loss guides training.Intermediate Planned - QQ-407Quantum Neural Networks (QNNs)
Map the data flow through a quantum neural network from classical features to measured outputs.Intermediate Planned - QQ-409Hybrid QML: Classical + Quantum Pipelines
Design the handoff between classical preprocessing, a quantum model and classical evaluation.Intermediate Planned - QQ-410QML in PennyLane: Hands-On
Assemble a small PennyLane QML experiment with measured predictions and reproducible configuration.Intermediate Planned - QQ-411QML in Qiskit Machine Learning
Configure a Qiskit Machine Learning workflow and compare its predictions with a baseline.Intermediate Planned - QQ-413Quantum Reinforcement Learning Basics
Identify where a quantum component could fit into reinforcement learning and specify the role of the environment and policy.Intermediate Planned - QQ-414QML for Classification: A Worked Case
Compare prediction errors from a small quantum classifier and a comparable classical model on the same data split.Intermediate Planned - QQ-415QML for Anomaly Detection
Define an anomaly score and assess how class imbalance changes a QML experiment's evaluation.Intermediate Planned - QQ-418When QML Helps, and When Classical Wins
Assess whether an observed performance difference can be attributed to the quantum component under the stated controls.Intermediate Planned - QQ-419QML Data: Preparing, Cleaning & Encoding
Plan data cleaning and feature preparation so the quantum encoding receives a stable input representation.Intermediate Planned - QQ-424Data Re-Uploading and Circuit Expressivity
Explain how repeated feature uploads affect a circuit model's functional capacity and cost.Intermediate Planned - QQ-425Feature Scaling for Angle-Encoding Models
Compare scale choices for a fixed encoding and check for feature compression or periodic ambiguity.Intermediate Planned - QQ-426Classical Surrogates for Quantum Model Outputs
Compare a small quantum model against a surrogate and identify what the surrogate captures.Intermediate Planned - QQ-427Train, Validation and Test Boundaries in QML
Design data partitions and guard against leakage in feature selection and tuning.Intermediate Planned - QQ-428Choosing Encodings Under Qubit Constraints
Compare feature reduction and re-encoding strategies under a fixed model width.Intermediate Planned
Advanced 15 planned
- QQ-408Training QNNs: Gradients & Barren Plateaus
Examine gradient estimates and diagnose conditions under which they become hard to resolve.Advanced Planned - QQ-412Quantum Generative Models
Compare quantum generative modelling approaches by representation, sampling demand and evaluation criteria.Advanced Planned - QQ-416QML for Time Series & Forecasting
Design a forecasting comparison that preserves temporal order and avoids leakage.Advanced Planned - QQ-417Evaluating QML: Honest Benchmarks
Report the quality, compute and sampling metrics needed to evaluate QML against a classical alternative.Advanced Planned - QQ-420Deploying a QML Model
Plan service interfaces, latency checks and monitoring for a hybrid QML prototype.Advanced Planned - QQ-421QML Ethics, Bias & Governance
Identify data governance, bias and transparency issues that persist when a model includes a quantum component.Advanced Planned - QQ-422QML Capstone: Build & Benchmark a Classifier
Define, train and report a bounded QML classifier study with a corresponding classical baseline.Advanced Planned - QQ-429Noise-Aware QML Training
Plan an experiment that tests whether a model trained under a noise model generalises to another condition.Advanced Planned - QQ-430Kernel Alignment and Kernel Concentration
Interpret kernel statistics that flag label mismatch or loss of useful variation between data points.Advanced Planned - QQ-431Data Access and QRAM Assumptions
Identify data-loading costs that change the plausibility of an end-to-end QML claim.Advanced Planned - QQ-432Gradient-Free Optimisers for Shot-Limited QML
Compare optimiser behaviour and stopping rules when model scores are based on noisy samples.Advanced Planned - QQ-433Quantum Generators and Distribution Metrics
Choose evaluation metrics that expose mode loss and sampling differences in generative experiments.Advanced Planned - QQ-434Hyperparameter Search Under a Matched Compute Budget
Design a tuning comparison that tracks resource expenditure for both quantum and classical models.Advanced Planned - QQ-435Error Mitigation for Quantum Model Inference
Estimate the sampling overhead and sensitivity trade-offs of mitigation in a fixed inference experiment.Advanced Planned - QQ-436MLOps for Hybrid Quantum Experiments
Version data, circuit specifications, backend settings and model results together to support reruns.Advanced Planned
Expert 4 planned
- QQ-437Statistical Power in QML Comparisons
Plan repeat runs and uncertainty estimates for comparing QML models with matched baselines.Expert Planned - QQ-438Analysing Trainability Before a QML Pilot
Connect model architecture, initialisation and objective choice to observable signs of poor trainability.Expert Planned - QQ-439Quantum Models for Quantum Data
Distinguish models that consume quantum states from models that encode conventional datasets, and compare their evaluation requirements.Expert Planned - QQ-440Hardware Transfer in Quantum Learning Pipelines
Evaluate how calibration changes and compilation variance affect a trained quantum model's reported performance.Expert Planned
Specialist 3 planned
- QQ-441Learning from Quantum Measurements with Classical Shadows
Interpret how measurement samples can support learning about a state under stated observable and sample assumptions.Specialist Planned - QQ-442Audit of a Claimed Quantum Learning Advantage
Review the data-access model, resource budget, classical competitors and uncertainty of a published claim.Specialist Planned - QQ-443Symmetry-Preserving Models for Quantum Learning
Analyse a circuit design that respects a known data symmetry and specify tests for whether it does so.Specialist Planned