Quant²AI – An End-to-End Quantum AI Benchmarking Framework
summary
A collaborative end-to-end benchmarking suite built for QML that runs on HPC and real quantum hardware (IQM, IBM) and simulators, uses Slurm to spawn fresh Python environments for reproducibility, and records circuit metrics (depth, qubits), ML scores (precision, recall) and custom quantum metrics with bootstrapped aggregation. It ships reference pipelines and datasets (Iris, MNIST, concrete panel crack images), offers a modular interchangeable pipeline and visual exports, and enables fair classical vs quantum comparisons as a scalable, reproducible benchmarking framework.
AI-written summary · about
chapters (7)
- 0:00Quant²AI project intro
- 2:48Quantum ML benchmarking challenges
- 4:59Framework goals
- 6:25Modular pipeline & HPC
- 9:13Metrics & visualization tools
- 11:00Pre-built pipelines & models
- 12:46Summary
related talks
20mQuantum Computing as a Service- Cloud-based and automized QML Solu
47mQuantum Machine Learning: Cutting Through the Buzzword BS
15mAccelerQ: Accelerating Quantum Eigensolvers With Machine Learning on Quantum Simulators
48mGetting Started with Quantum Programming
01h 07mQuantum architecture for utility scale with HPC, AI and Quantum
20mLeveraging Quantum Computing applications for companies of all sizes
34mQumat: Apache Mahout Quantum Compute
42mBuilding Hybrid Quantum-Classical Pipelines : A Practic...