Brain-Inspired Quantum Neural Architectures for Pattern Recognition: Integrating QSNN and QLSTM

TL;DR

This paper introduces a brain-inspired quantum neural architecture combining QSNN and QLSTM for anomaly detection in credit card fraud, mimicking sensory and memory brain functions.

Contribution

It presents a novel two-stage quantum neural model inspired by brain mechanisms, integrating QSNN and QLSTM for improved pattern recognition.

Findings

Model emulates brain's sensory and memory processing.

Comparison with classical and quantum models shows potential advantages.

Framework applicable to various anomaly detection tasks.

Abstract

Recent advances in the fields of deep learning and quantum computing have paved the way for innovative developments in artificial intelligence. In this manuscript, we leverage these cutting-edge technologies to introduce a novel model that emulates the intricate functioning of the human brain, designed specifically for the detection of anomalies such as fraud in credit card transactions. Leveraging the synergies of Quantum Spiking Neural Networks (QSNN) and Quantum Long Short-Term Memory (QLSTM) architectures, our approach is developed in two distinct stages, closely mirroring the information processing mechanisms found in the brain's sensory and memory systems. In the initial stage, similar to the brain's hypothalamus, we extract low-level information from the data, emulating sensory data processing patterns. In the subsequent stage, resembling the hippocampus, we process this information at a higher level, capturing and memorizing correlated patterns. We will compare this model with other quantum models such as Quantum Neural Networks among others and their corresponding classical models.