Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning
Quantum-inspired computing is an emerging research area, which has significantly improved the capabilities of conventional algorithms. In general, quantum-inspired hopfield associative memory (QHAM) has demonstrated quantum information processing in neural structures. This has resulted in an exponen...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2018
|
| Subjects: |
| _version_ | 1796961409359151104 |
|---|---|
| author | Masuyama, Naoki Loo, Chu Kiong Seera, Manjeevan Kubota, Naoyuki |
| author_facet | Masuyama, Naoki Loo, Chu Kiong Seera, Manjeevan Kubota, Naoyuki |
| author_sort | Masuyama, Naoki |
| collection | UM |
| description | Quantum-inspired computing is an emerging research area, which has significantly improved the capabilities of conventional algorithms. In general, quantum-inspired hopfield associative memory (QHAM) has demonstrated quantum information processing in neural structures. This has resulted in an exponential increase in storage capacity while explaining the extensive memory, and it has the potential to illustrate the dynamics of neurons in the human brain when viewed from quantum mechanics perspective although the application of QHAM is limited as an autoassociation. We introduce a quantum-inspired multidirectional associative memory (QMAM) with a one-shot learning model, and QMAM with a self-convergent iterative learning model (IQMAM) based on QHAM in this paper. The self-convergent iterative learning enables the network to progressively develop a resonance state, from inputs to outputs. The simulation experiments demonstrate the advantages of QMAM and IQMAM, especially the stability to recall reliability. |
| first_indexed | 2024-03-06T05:53:49Z |
| format | Article |
| id | um.eprints-21322 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T05:53:49Z |
| publishDate | 2018 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | um.eprints-213222019-05-27T05:00:00Z http://eprints.um.edu.my/21322/ Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning Masuyama, Naoki Loo, Chu Kiong Seera, Manjeevan Kubota, Naoyuki QA75 Electronic computers. Computer science Quantum-inspired computing is an emerging research area, which has significantly improved the capabilities of conventional algorithms. In general, quantum-inspired hopfield associative memory (QHAM) has demonstrated quantum information processing in neural structures. This has resulted in an exponential increase in storage capacity while explaining the extensive memory, and it has the potential to illustrate the dynamics of neurons in the human brain when viewed from quantum mechanics perspective although the application of QHAM is limited as an autoassociation. We introduce a quantum-inspired multidirectional associative memory (QMAM) with a one-shot learning model, and QMAM with a self-convergent iterative learning model (IQMAM) based on QHAM in this paper. The self-convergent iterative learning enables the network to progressively develop a resonance state, from inputs to outputs. The simulation experiments demonstrate the advantages of QMAM and IQMAM, especially the stability to recall reliability. Institute of Electrical and Electronics Engineers (IEEE) 2018 Article PeerReviewed Masuyama, Naoki and Loo, Chu Kiong and Seera, Manjeevan and Kubota, Naoyuki (2018) Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning. IEEE Transactions on Neural Networks and Learning Systems, 29 (4). pp. 1058-1068. ISSN 2162-237X, DOI https://doi.org/10.1109/TNNLS.2017.2653114 <https://doi.org/10.1109/TNNLS.2017.2653114>. https://doi.org/10.1109/TNNLS.2017.2653114 doi:10.1109/TNNLS.2017.2653114 |
| spellingShingle | QA75 Electronic computers. Computer science Masuyama, Naoki Loo, Chu Kiong Seera, Manjeevan Kubota, Naoyuki Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning |
| title | Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning |
| title_full | Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning |
| title_fullStr | Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning |
| title_full_unstemmed | Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning |
| title_short | Quantum-Inspired Multidirectional Associative Memory With a Self-Convergent Iterative Learning |
| title_sort | quantum inspired multidirectional associative memory with a self convergent iterative learning |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT masuyamanaoki quantuminspiredmultidirectionalassociativememorywithaselfconvergentiterativelearning AT loochukiong quantuminspiredmultidirectionalassociativememorywithaselfconvergentiterativelearning AT seeramanjeevan quantuminspiredmultidirectionalassociativememorywithaselfconvergentiterativelearning AT kubotanaoyuki quantuminspiredmultidirectionalassociativememorywithaselfconvergentiterativelearning |