Hybrid Quantum Neural Networks (HQNN) Research
I am currently engaged in a remote research internship at Trinity College Dublin under the guidance of Dr. Subramanyam Murala, focusing on the development of Hybrid Quantum Neural Networks (HQNNs) for image classification tasks. This work involves integrating Classical Convolutional Neural Networks (CNNs) with Parameterized Quantum Circuits (PQC) to enhance the capabilities of Quantum Convolutional Neural Networks (QCNNs).
Research Objectives
- Design and Implementation of HQNNs: Combining classical CNN layers with PQCs to optimize image classification tasks.
- Exploration of PQCs in QCNNs: Investigating their role in enhancing non-linearity and improving model performance.
- Optimization Techniques: Implementing various quantum-classical hybrid learning techniques to improve accuracy and efficiency.
- Simulation and Real Hardware Testing: Running experiments on quantum simulators and IBM’s quantum hardware to validate model performance.
Tools & Technologies Used
- Qiskit: For designing and simulating quantum circuits.
- Pennylane: For integrating PQCs into the classical CNN framework.
- PyTorch & TensorFlow: For implementing and training the hybrid neural network models.
