SciPost Submission Page
Noisy Quantum Convolutional Neural Network
by Zeyu Fan, Jonathan Wei Zhong Lau, Leong-Chuan Kwek
Submission summary
| Authors (as registered SciPost users): | Zeyu Fan |
| Submission information | |
|---|---|
| Preprint Link: | scipost_202407_00021v1 (pdf) |
| Date submitted: | 2024-07-12 07:01 |
| Submitted by: | Fan, Zeyu |
| Submitted to: | SciPost Physics |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approach: | Computational |
Abstract
his study investigates the potential performance enhancement of a quantum convolutional neu- ral network (QCNN) through the introduction of noise, akin to the benefits observed in classical convolutional neural networks (CNNs) with added Gaussian noise. While Gaussian noise has proven advantageous for classical CNNs in terms of training speed, accuracy, and generalizability to unseen data, the impact of noise on quantum counterparts remains unexplored. We specifically examine three types of quantum noise: decoherence, Gaussian noise from imperfect quantum gates and ex- perimental error, and systematic quantum noise that may be introduced to input states during state creation. Our analysis aims to quantify the effects of these noise sources on the operation of QCNNs and proposes strategies to mitigate potential drawbacks.
Author indications on fulfilling journal expectations
- Provide a novel and synergetic link between different research areas.
- Open a new pathway in an existing or a new research direction, with clear potential for multi-pronged follow-up work
- Detail a groundbreaking theoretical/experimental/computational discovery
- Present a breakthrough on a previously-identified and long-standing research stumbling block