This repository showcases the application of Quantum Machine Learning (QML) to traditional machine learning tasks, such as classification regression, and optimisation. The purpose is twofold:

The goal of this repository is twofold:

• To explore and advance understanding in state-of-the-art Quantum Machine Learning techniques.
• To demonstrate my expertise in Quantum Machine Learning as a foundation for future career opportunities.

This repository currently includes the following areas of focus:

• Classification: Implementations include multiclass classification models utilising:

  • Hybrid Models: Deep neural networks combined with quantum neural networks.
  • Fully Quantum Models: Quantum neural networks designed for classification tasks.
  • Quantum Support Vector Machines: Models based on quantum support vector machine techniques.

• Regression: We investigate quantum algorithms for regression tasks using classical datasets, featuring implementations of:

  • Hybrid Models: Deep neural networks paired with quantum neural networks.
  • Fully Quantum Models: Quantum neural networks tailored for regression.
  • Quantum Support Vector Machines: Regression models based on quantum support vector machine approaches.

• Optimisation Techniques:

  • Quantum Bayesian Optimization, specifically employing Quantum Gaussian Processes to enhance optimization strategies.

Planned additions and improvements include:

• Development of QML algorithms focused on Natural Language Processing (NLP).
• Exploration and implementation of Quantum Reinforcement Learning models.
• Performance Evaluation: Comparative analysis of quantum versus classical algorithms to assess potential advantages in terms of accuracy, computational complexity, and scalability.

Due to the rapid evolution of the Qiskit framework, some parts of this repository may become incompatible in the future. I am actively working on updates, but there may be occasional delays in implementation.

• qiskit >=1.3
• qiskit-algorithms >=0.3
• qiskit-nature >=0.7
• qiskit-machine-learning >=0.8
• qiskit-optimization >=0.6
• qiskit-aer >=0.16
• scikit-learn >=1.5
• torch >=2.4
• matplotlib >=3.9
• seaborn >=3.9
• pandas >=2.2