Episodic Memory and Information Recognition Using Solitonic Neural Networks Based on Photorefractive Plasticity
Neuromorphic models are proving capable of performing complex machine learning tasks, overcoming the structural limitations imposed by software algorithms and electronic architectures. Recently, both supervised and unsupervised learnings were obtained in photonic neurons by means of spatial-soliton-...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/11/5585 |
| _version_ | 1797494125964034048 |
|---|---|
| author | Alessandro Bile Hamed Tari Eugenio Fazio |
| author_facet | Alessandro Bile Hamed Tari Eugenio Fazio |
| author_sort | Alessandro Bile |
| collection | DOAJ |
| description | Neuromorphic models are proving capable of performing complex machine learning tasks, overcoming the structural limitations imposed by software algorithms and electronic architectures. Recently, both supervised and unsupervised learnings were obtained in photonic neurons by means of spatial-soliton-waveguide X-junctions. This paper investigates the behavior of networks based on these solitonic neurons, which are capable of performing complex tasks such as bit-to-bit information memorization and recognition. By exploiting photorefractive nonlinearity as if it were a biological neuroplasticity, the network modifies and adapts to the incoming signals, memorizing and recognizing them (photorefractive plasticity). The information processing and storage result in a plastic modification of the network interconnections. Theoretical description and numerical simulation of solitonic networks are reported and applied to the processing of 4-bit information. |
| first_indexed | 2024-03-10T01:29:50Z |
| format | Article |
| id | doaj.art-8cbfc3a5dcb9468f88f32846af3df718 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T01:29:50Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-8cbfc3a5dcb9468f88f32846af3df7182023-11-23T13:44:17ZengMDPI AGApplied Sciences2076-34172022-05-011211558510.3390/app12115585Episodic Memory and Information Recognition Using Solitonic Neural Networks Based on Photorefractive PlasticityAlessandro Bile0Hamed Tari1Eugenio Fazio2Department of Fundamental and Applied Sciences for Engineering, Sapienza Università di Roma, Via A. Scarpa 16, 00161 Roma, ItalyDepartment of Fundamental and Applied Sciences for Engineering, Sapienza Università di Roma, Via A. Scarpa 16, 00161 Roma, ItalyDepartment of Fundamental and Applied Sciences for Engineering, Sapienza Università di Roma, Via A. Scarpa 16, 00161 Roma, ItalyNeuromorphic models are proving capable of performing complex machine learning tasks, overcoming the structural limitations imposed by software algorithms and electronic architectures. Recently, both supervised and unsupervised learnings were obtained in photonic neurons by means of spatial-soliton-waveguide X-junctions. This paper investigates the behavior of networks based on these solitonic neurons, which are capable of performing complex tasks such as bit-to-bit information memorization and recognition. By exploiting photorefractive nonlinearity as if it were a biological neuroplasticity, the network modifies and adapts to the incoming signals, memorizing and recognizing them (photorefractive plasticity). The information processing and storage result in a plastic modification of the network interconnections. Theoretical description and numerical simulation of solitonic networks are reported and applied to the processing of 4-bit information.https://www.mdpi.com/2076-3417/12/11/5585artificial intelligenceepisodic memoryneuromorphic systemsneuroplasticityneural networkslearning |
| spellingShingle | Alessandro Bile Hamed Tari Eugenio Fazio Episodic Memory and Information Recognition Using Solitonic Neural Networks Based on Photorefractive Plasticity Applied Sciences artificial intelligence episodic memory neuromorphic systems neuroplasticity neural networks learning |
| title | Episodic Memory and Information Recognition Using Solitonic Neural Networks Based on Photorefractive Plasticity |
| title_full | Episodic Memory and Information Recognition Using Solitonic Neural Networks Based on Photorefractive Plasticity |
| title_fullStr | Episodic Memory and Information Recognition Using Solitonic Neural Networks Based on Photorefractive Plasticity |
| title_full_unstemmed | Episodic Memory and Information Recognition Using Solitonic Neural Networks Based on Photorefractive Plasticity |
| title_short | Episodic Memory and Information Recognition Using Solitonic Neural Networks Based on Photorefractive Plasticity |
| title_sort | episodic memory and information recognition using solitonic neural networks based on photorefractive plasticity |
| topic | artificial intelligence episodic memory neuromorphic systems neuroplasticity neural networks learning |
| url | https://www.mdpi.com/2076-3417/12/11/5585 |
| work_keys_str_mv | AT alessandrobile episodicmemoryandinformationrecognitionusingsolitonicneuralnetworksbasedonphotorefractiveplasticity AT hamedtari episodicmemoryandinformationrecognitionusingsolitonicneuralnetworksbasedonphotorefractiveplasticity AT eugeniofazio episodicmemoryandinformationrecognitionusingsolitonicneuralnetworksbasedonphotorefractiveplasticity |