Understanding Logical-Shift Error Propagation in Quanvolutional Neural Networks
Quanvolutional neural networks (QNNs) have been successful in image classification, exploiting inherent quantum capabilities to improve performance of traditional convolution. Unfortunately, the qubit's reliability can be a significant issue for QNNs inference, since its logical state can...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Quantum Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10458381/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583959673831424 |
|---|---|
| author | Marzio Vallero Emanuele Dri Edoardo Giusto Bartolomeo Montrucchio Paolo Rech |
| author_facet | Marzio Vallero Emanuele Dri Edoardo Giusto Bartolomeo Montrucchio Paolo Rech |
| author_sort | Marzio Vallero |
| collection | DOAJ |
| description | Quanvolutional neural networks (QNNs) have been successful in image classification, exploiting inherent quantum capabilities to improve performance of traditional convolution. Unfortunately, the qubit's reliability can be a significant issue for QNNs inference, since its logical state can be altered by both intrinsic noise and by the interaction with natural radiation. In this article, we aim at investigating the propagation of logical-shift errors (i.e., the unexpected modification of the qubit state) in QNNs. We propose a bottom–up evaluation reporting data from 13 322 547 200 logical-shift injections. We characterize the error propagation in the quantum circuit implementing a single convolution and then in various designs of the same QNN, varying the dataset and the network depth. We track the logical-shift error propagation through the qubits, channels, and subgrids, identifying the faults that are more likely to cause misclassifications. We found that up to 10% of the injections in the quanvolutional layer cause misclassification and even logical-shifts of small magnitude can be sufficient to disturb the network functionality. Our detailed analysis shows that corruptions in the qubits' state that alter their probability amplitude are more critical than the ones altering their phase, that some object classes are more likely than others to be corrupted, that the criticality of subgrids depends on the dataset, and that the control qubits, once corrupted, are more likely to modify the QNN output than the target qubits. |
| format | Article |
| id | doaj-art-0f6faecd1e364bfb84c95754fe533251 |
| institution | Kabale University |
| issn | 2689-1808 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Quantum Engineering |
| spelling | doaj-art-0f6faecd1e364bfb84c95754fe5332512025-01-28T00:02:19ZengIEEEIEEE Transactions on Quantum Engineering2689-18082024-01-01511410.1109/TQE.2024.337288010458381Understanding Logical-Shift Error Propagation in Quanvolutional Neural NetworksMarzio Vallero0https://orcid.org/0009-0002-1292-8140Emanuele Dri1https://orcid.org/0000-0002-5144-1514Edoardo Giusto2https://orcid.org/0000-0001-8371-6685Bartolomeo Montrucchio3https://orcid.org/0000-0003-0065-8614Paolo Rech4https://orcid.org/0000-0002-0821-1879University of Trento, Trento, ItalyPolitecnico di Torino, Torino, ItalyPolitecnico di Torino, Torino, ItalyPolitecnico di Torino, Torino, ItalyUniversity of Trento, Trento, ItalyQuanvolutional neural networks (QNNs) have been successful in image classification, exploiting inherent quantum capabilities to improve performance of traditional convolution. Unfortunately, the qubit's reliability can be a significant issue for QNNs inference, since its logical state can be altered by both intrinsic noise and by the interaction with natural radiation. In this article, we aim at investigating the propagation of logical-shift errors (i.e., the unexpected modification of the qubit state) in QNNs. We propose a bottom–up evaluation reporting data from 13 322 547 200 logical-shift injections. We characterize the error propagation in the quantum circuit implementing a single convolution and then in various designs of the same QNN, varying the dataset and the network depth. We track the logical-shift error propagation through the qubits, channels, and subgrids, identifying the faults that are more likely to cause misclassifications. We found that up to 10% of the injections in the quanvolutional layer cause misclassification and even logical-shifts of small magnitude can be sufficient to disturb the network functionality. Our detailed analysis shows that corruptions in the qubits' state that alter their probability amplitude are more critical than the ones altering their phase, that some object classes are more likely than others to be corrupted, that the criticality of subgrids depends on the dataset, and that the control qubits, once corrupted, are more likely to modify the QNN output than the target qubits.https://ieeexplore.ieee.org/document/10458381/Fault injectionfault tolerancequantum computing (QC)quantum machine learning (QML)reliability evaluation |
| spellingShingle | Marzio Vallero Emanuele Dri Edoardo Giusto Bartolomeo Montrucchio Paolo Rech Understanding Logical-Shift Error Propagation in Quanvolutional Neural Networks IEEE Transactions on Quantum Engineering Fault injection fault tolerance quantum computing (QC) quantum machine learning (QML) reliability evaluation |
| title | Understanding Logical-Shift Error Propagation in Quanvolutional Neural Networks |
| title_full | Understanding Logical-Shift Error Propagation in Quanvolutional Neural Networks |
| title_fullStr | Understanding Logical-Shift Error Propagation in Quanvolutional Neural Networks |
| title_full_unstemmed | Understanding Logical-Shift Error Propagation in Quanvolutional Neural Networks |
| title_short | Understanding Logical-Shift Error Propagation in Quanvolutional Neural Networks |
| title_sort | understanding logical shift error propagation in quanvolutional neural networks |
| topic | Fault injection fault tolerance quantum computing (QC) quantum machine learning (QML) reliability evaluation |
| url | https://ieeexplore.ieee.org/document/10458381/ |
| work_keys_str_mv | AT marziovallero understandinglogicalshifterrorpropagationinquanvolutionalneuralnetworks AT emanueledri understandinglogicalshifterrorpropagationinquanvolutionalneuralnetworks AT edoardogiusto understandinglogicalshifterrorpropagationinquanvolutionalneuralnetworks AT bartolomeomontrucchio understandinglogicalshifterrorpropagationinquanvolutionalneuralnetworks AT paolorech understandinglogicalshifterrorpropagationinquanvolutionalneuralnetworks |