Hybrid Quantum-Classical Machine Learning using Qiskit
summary
Claims a working hybrid framework built with Qiskit 1.0.2 that encodes classical text into quantum circuits using a quantum feature map and runs QSVC and VQC models (simulated, simulator only). Experiments on Twitter and Bengali news headlines use PCA and Haar wavelet compression, report ~70–72% accuracy comparable to classical SVM, find VQC trains fastest, and show classical accuracy collapses under heavy compression while quantum-classical models remain stable.
AI-written summary · about
chapters (11)
- 0:00Introduction and overview
- 0:42Research group background
- 1:14Quantum research branches
- 2:01Quantum computing fundamentals
- 11:51Data preprocessing methodology
- 12:45Dimension reduction techniques
- 14:26QML model implementation
- 20:54Performance evaluation
- 22:59Compression impact study
- 24:46Installation and setup
- 25:28Q&A and conclusion
related talks
27mWhat are quantum computers, and how can we train them in Python?
03h 06mQiskit for Python Developers – Workshop
01h 36mHands on Quantum Computer
30m"Quantum Computing with Qiskit in Galaxy"
22mGUPPY: Pythonic Quantum-Classical Programming
01h 27mQuantum Computing with Python
27mQuantum Computing with Python: From Qubits to Circuits
24mPython for QKD...