From first principles
to research practice.
A suggested sequence for software engineers, quantum researchers and machine-learning practitioners.
Phase I · PrerequisitesPhase II · Core QMLPhase III · Research frontiersPhase IV · Evaluation and deployment
Phase I · Establish foundations
Milestone: Implement a single-qubit encoder and verify its measured expectation analytically.
Stage 01Mathematical & quantum foundationsFour lessons · Chapter 1Stage 02Classical ML foundationsFour lessons · Chapter 2Stage 03Data encoding & feature mapsFour lessons · Chapter 3
Phase II · Build and compare models
Milestone: Train a tiny VQC and evaluate a fidelity-kernel SVM against an RBF SVM.
Stage 04Variational quantum modelsFour lessons · Chapter 4Stage 05Quantum kernels & learning theoryFour lessons · Chapter 5Stage 06Optimization, trainability & noiseFour lessons · Chapter 6
Phase III · Explore specialized models
Milestone: Fit a Born machine to a four-outcome distribution and inspect shot noise.
Stage 07Quantum generative learningFour lessons · Chapter 7Stage 08Quantum data & scientific MLFour lessons · Chapter 8Stage 09Reinforcement learning & sequential modelsFour lessons · Chapter 9Stage 10Algorithms, complexity & advantageFour lessons · Chapter 10
Phase IV · Test real value
Milestone: Produce a reproducible benchmark with matched data splits, multiple seeds and total-cost accounting.