TunnElQNN: A Hybrid Quantum-classical Neural Network for Efficient Learning

TL;DR

This paper introduces TunnElQNN, a hybrid quantum-classical neural network with a novel physics-inspired activation function, demonstrating improved performance over traditional models on multi-class classification tasks with overlapping classes.

Contribution

The work presents a new non-sequential hybrid architecture using a tunnelling diode activation function, combining quantum and classical layers for enhanced learning capabilities.

Findings

TunnElQNN outperforms ReLUQNN in classification accuracy.

Decision boundaries of TunnElQNN are more robust to class overlap.

Physics-inspired activation functions improve hybrid model expressiveness.

Abstract

Hybrid quantum-classical neural networks (HQCNNs) represent a promising frontier in machine learning, leveraging the complementary strengths of both models. In this work, we propose the development of TunnElQNN, a non-sequential architecture composed of alternating classical and quantum layers. Within the classical component, we employ the Tunnelling Diode Activation Function (TDAF), inspired by the I-V characteristics of quantum tunnelling. We evaluate the performance of this hybrid model on a synthetic dataset of interleaving half-circle for multi-class classification tasks with varying degrees of class overlap. The model is compared against a baseline hybrid architecture that uses the conventional ReLU activation function (ReLUQNN). Our results show that the TunnElQNN model consistently outperforms the ReLUQNN counterpart. Furthermore, we analyse the decision boundaries generated by TunnElQNN under different levels of class overlap and compare them to those produced by a neural network implementing TDAF within a fully classical architecture. These findings highlight the potential of integrating physics-inspired activation functions with quantum components to enhance the expressiveness and robustness of hybrid quantum-classical machine learning architectures.