Novel Complex-Valued Hopfield Neural Networks with Phase and Magnitude Quantization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918076878946304 |
|---|---|
| author | Ramamurthy, Garimella Valle, Marcos Eduardo Swamy, Tata Jagannadha |
| author_facet | Ramamurthy, Garimella Valle, Marcos Eduardo Swamy, Tata Jagannadha |
| contents | This research paper introduces two novel complex-valued Hopfield neural networks (CvHNNs) that incorporate phase and magnitude quantization. The first CvHNN employs a ceiling-type activation function that operates on the rectangular coordinate representation of the complex net contribution. The second CvHNN similarly incorporates phase and magnitude quantization but utilizes a ceiling-type activation function based on the polar coordinate representation of the complex net contribution. The proposed CvHNNs, with their phase and magnitude quantization, significantly increase the number of states compared to existing models in the literature, thereby expanding the range of potential applications for CvHNNs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00461 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Novel Complex-Valued Hopfield Neural Networks with Phase and Magnitude Quantization Ramamurthy, Garimella Valle, Marcos Eduardo Swamy, Tata Jagannadha Neural and Evolutionary Computing Artificial Intelligence This research paper introduces two novel complex-valued Hopfield neural networks (CvHNNs) that incorporate phase and magnitude quantization. The first CvHNN employs a ceiling-type activation function that operates on the rectangular coordinate representation of the complex net contribution. The second CvHNN similarly incorporates phase and magnitude quantization but utilizes a ceiling-type activation function based on the polar coordinate representation of the complex net contribution. The proposed CvHNNs, with their phase and magnitude quantization, significantly increase the number of states compared to existing models in the literature, thereby expanding the range of potential applications for CvHNNs. |
| title | Novel Complex-Valued Hopfield Neural Networks with Phase and Magnitude Quantization |
| topic | Neural and Evolutionary Computing Artificial Intelligence |
| url | https://arxiv.org/abs/2507.00461 |