Quantum Optimization for AI
Build a quantum annealing pipeline for combinatorial optimization — choose feature selection or graph partitioning, solve with simulated annealing, and optionally connect to D-Wave hardware.
"Select the optimal 8 features from 30 — annealing beats greedy by 5% accuracy"
6 Modules
Each module builds on the previous one. By the end, you have a complete production system.
- 1
Foundations
Brute-force QUBO solver + energy landscape
- 2
QUBO Formulation
Feature selection + graph partition QUBOs
- 3
Use Case Lab
Problem-specific QUBO (student choice)
- 4
Annealing Solver
SA solver with convergence analysis
- 5
Pipeline App
Interactive Next.js dashboard
- 6
Production & D-Wave
Benchmarks + portfolio piece
Production patterns you'll master
Synthetic data included
- Classification dataset (30 features)
- Social network graph (50 nodes)
- Pre-computed MI scores
- Correlation matrices
- Community ground truth
What you walk away with
Shareable portfolio
A public URL showing your module timeline, patterns mastered, and completion status.
All the code
Download everything as a ZIP — pipelines, guardrails, deployment configs. Yours forever.
Module walkthrough
Each module documented with deliverables and the production pattern you implemented.