Neuromorphic Computing via Fission‐based Broadband Frequency Generation
Abstract The performance limitations of traditional computer architectures have led to the rise of brain‐inspired hardware, with optical solutions gaining popularity due to the energy efficiency, high speed, and scalability of linear operations. However, the use of optics to emulate the synaptic act...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-12-01
|
| Series: | Advanced Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/advs.202303835 |
| _version_ | 1827582828814008320 |
|---|---|
| author | Bennet Fischer Mario Chemnitz Yi Zhu Nicolas Perron Piotr Roztocki Benjamin MacLellan Luigi Di Lauro A. Aadhi Cristina Rimoldi Tiago H. Falk Roberto Morandotti |
| author_facet | Bennet Fischer Mario Chemnitz Yi Zhu Nicolas Perron Piotr Roztocki Benjamin MacLellan Luigi Di Lauro A. Aadhi Cristina Rimoldi Tiago H. Falk Roberto Morandotti |
| author_sort | Bennet Fischer |
| collection | DOAJ |
| description | Abstract The performance limitations of traditional computer architectures have led to the rise of brain‐inspired hardware, with optical solutions gaining popularity due to the energy efficiency, high speed, and scalability of linear operations. However, the use of optics to emulate the synaptic activity of neurons has remained a challenge since the integration of nonlinear nodes is power‐hungry and, thus, hard to scale. Neuromorphic wave computing offers a new paradigm for energy‐efficient information processing, building upon transient and passively nonlinear interactions between optical modes in a waveguide. Here, an implementation of this concept is presented using broadband frequency conversion by coherent higher‐order soliton fission in a single‐mode fiber. It is shown that phase encoding on femtosecond pulses at the input, alongside frequency selection and weighting at the system output, makes transient spectro‐temporal system states interpretable and allows for the energy‐efficient emulation of various digital neural networks. The experiments in a compact, fully fiber‐integrated setup substantiate an anticipated enhancement in computational performance with increasing system nonlinearity. The findings suggest that broadband frequency generation, accessible on‐chip and in‐fiber with off‐the‐shelf components, may challenge the traditional approach to node‐based brain‐inspired hardware design, ultimately leading to energy‐efficient, scalable, and dependable computing with minimal optical hardware requirements. |
| first_indexed | 2024-03-08T22:58:13Z |
| format | Article |
| id | doaj.art-20ae07be913b402384a9da8c351861a9 |
| institution | Directory Open Access Journal |
| issn | 2198-3844 |
| language | English |
| last_indexed | 2024-03-08T22:58:13Z |
| publishDate | 2023-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Science |
| spelling | doaj.art-20ae07be913b402384a9da8c351861a92023-12-16T04:16:14ZengWileyAdvanced Science2198-38442023-12-011035n/an/a10.1002/advs.202303835Neuromorphic Computing via Fission‐based Broadband Frequency GenerationBennet Fischer0Mario Chemnitz1Yi Zhu2Nicolas Perron3Piotr Roztocki4Benjamin MacLellan5Luigi Di Lauro6A. Aadhi7Cristina Rimoldi8Tiago H. Falk9Roberto Morandotti10Institut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaInstitut National de la Recherche Scientifique – Énergie Matériaux et Télécommunications 1650 Blvd. Lionel‐Boulet Varennes Quebec J3X1S2 CanadaAbstract The performance limitations of traditional computer architectures have led to the rise of brain‐inspired hardware, with optical solutions gaining popularity due to the energy efficiency, high speed, and scalability of linear operations. However, the use of optics to emulate the synaptic activity of neurons has remained a challenge since the integration of nonlinear nodes is power‐hungry and, thus, hard to scale. Neuromorphic wave computing offers a new paradigm for energy‐efficient information processing, building upon transient and passively nonlinear interactions between optical modes in a waveguide. Here, an implementation of this concept is presented using broadband frequency conversion by coherent higher‐order soliton fission in a single‐mode fiber. It is shown that phase encoding on femtosecond pulses at the input, alongside frequency selection and weighting at the system output, makes transient spectro‐temporal system states interpretable and allows for the energy‐efficient emulation of various digital neural networks. The experiments in a compact, fully fiber‐integrated setup substantiate an anticipated enhancement in computational performance with increasing system nonlinearity. The findings suggest that broadband frequency generation, accessible on‐chip and in‐fiber with off‐the‐shelf components, may challenge the traditional approach to node‐based brain‐inspired hardware design, ultimately leading to energy‐efficient, scalable, and dependable computing with minimal optical hardware requirements.https://doi.org/10.1002/advs.202303835artificial neural networkshigher‐order soliton fissionsneuromorphic computingnonlinear fiber opticsoptics and photonics |
| spellingShingle | Bennet Fischer Mario Chemnitz Yi Zhu Nicolas Perron Piotr Roztocki Benjamin MacLellan Luigi Di Lauro A. Aadhi Cristina Rimoldi Tiago H. Falk Roberto Morandotti Neuromorphic Computing via Fission‐based Broadband Frequency Generation Advanced Science artificial neural networks higher‐order soliton fissions neuromorphic computing nonlinear fiber optics optics and photonics |
| title | Neuromorphic Computing via Fission‐based Broadband Frequency Generation |
| title_full | Neuromorphic Computing via Fission‐based Broadband Frequency Generation |
| title_fullStr | Neuromorphic Computing via Fission‐based Broadband Frequency Generation |
| title_full_unstemmed | Neuromorphic Computing via Fission‐based Broadband Frequency Generation |
| title_short | Neuromorphic Computing via Fission‐based Broadband Frequency Generation |
| title_sort | neuromorphic computing via fission based broadband frequency generation |
| topic | artificial neural networks higher‐order soliton fissions neuromorphic computing nonlinear fiber optics optics and photonics |
| url | https://doi.org/10.1002/advs.202303835 |
| work_keys_str_mv | AT bennetfischer neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT mariochemnitz neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT yizhu neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT nicolasperron neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT piotrroztocki neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT benjaminmaclellan neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT luigidilauro neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT aaadhi neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT cristinarimoldi neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT tiagohfalk neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration AT robertomorandotti neuromorphiccomputingviafissionbasedbroadbandfrequencygeneration |