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

TL;DR

This work introduces TunnElQNN, a non-sequential hybrid quantum-classical neural network that integrates a physics-inspired TDAF activation within classical layers and a two-qubit quantum block with AngleEmbedding and a closed-ring entangler. On a synthetic three-class interleaving half-circle dataset, TunnElQNN outperforms a ReLU-based HQCNN and a classical TDAF network, delivering smoother decision boundaries and higher accuracy across varying class overlaps. Key findings include improved generalisation via physics-informed nonlinearity and quantum feature encoding, with deeper quantum layers up to four providing performance gains before diminishing returns or optimization challenges arise. The results highlight the practical potential of combining physics-based activations with quantum components for robust pattern recognition in hybrid architectures, and suggest pathways toward hardware-aware implementations on NISQ devices and analog quantum co-processors.

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.

Figures (6)

• Figure 1: Hybrid quantum-classical neural network architecture combining classical layers with Tunnelling-Diode Activation Function (TDAF) units and a 2-qubit quantum layer featuring AngleEmbedding and entangling operations. The model processes input data through alternating classical and quantum layers to produce a 3-neuron output, leveraging both classical and quantum computational advantages.
• Figure 2: (a) The I–V response of the tunnel diode. (b) Its corresponding differential conductance.
• Figure 3: Three interleaving half-circles dataset with $n=2000$ samples. Data points are coloured by class: Class P for Purple , Class C for Cyan, and Class R for Red. A horizontal shift of 1.5 arb. Units was applied to separate the respective half-circles.
• Figure 4: Comparison of TunnElQNN and ReLUQNN on the synthetic 2D three-class interleaving half-circles dataset. The first row illustrates the decision boundaries learned by each model (a: TunnElQNN, b: ReLUQNN). The second row shows the confusion matrices, highlighting classification performance (c: TunnElQNN, d: ReLUQNN). The third row presents training accuracy and loss curves, demonstrating convergence behaviour (e: TunnElQNN, f: ReLUQNN). TunnElQNN exhibits smoother decision regions and achieves 99% training accuracy, indicating better generalisation, while ReLUQNN reaches 80% accuracy. achieves higher classification accuracy with minimal misclassification across classes P, R, and C. Training curves showing loss (red, left axis) and accuracy (blue, right axis) over 150 epochs for TunnElQNN (e) and ReLUQNN (f) models.
• Figure 5: Comparison of the performance of TunnElQNN and a classical neural network using TDAF on the synthetic 2D three-class interleaving half-circles dataset with varying class horizontal separation. Decision boundaries are shown for increasing levels of separation: (a) separation = 0.2 arb. Units (high overlap), (b) separation = 1 arb. Units (moderate overlap), and (c) separation = 3 arb. Units (well-separated classes). TunnElQNN consistently learns accurate decision boundaries across all levels of overlap, while the standalone TDAF-based network performs reliably only when the data is well separated.