Chalcogenide phase-change devices for neuromorphic photonic computing
The integration of artificial intelligence systems into daily applications like speech recognition and autonomous driving rapidly increases the amount of data generated and processed. However, satisfying the hardware requirements with the conventional von Neumann architecture remains challenging due...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
American Institute of Physics
2021
|
| _version_ | 1826307597650624512 |
|---|---|
| author | Brueckerhoff-Plueckelmann, F Feldmann, J Wright, CD Bhaskaran, H Pernice, WHP |
| author_facet | Brueckerhoff-Plueckelmann, F Feldmann, J Wright, CD Bhaskaran, H Pernice, WHP |
| author_sort | Brueckerhoff-Plueckelmann, F |
| collection | OXFORD |
| description | The integration of artificial intelligence systems into daily applications like speech recognition and autonomous driving rapidly increases the amount of data generated and processed. However, satisfying the hardware requirements with the conventional von Neumann architecture remains challenging due to the von Neumann bottleneck. Therefore, new architectures inspired by the working principles of the human brain are developed, and they are called neuromorphic computing. The key principles of neuromorphic computing are in-memory computing to reduce data shuffling and parallelization to decrease computation time. One promising framework for neuromorphic computing is phase-change photonics. By switching to the optical domain, parallelization is inherently possible by wavelength division multiplexing, and high modulation speeds can be deployed. Non-volatile phase-change materials are used to perform multiplications and non-linear operations in an energetically efficient manner. Here, we present two prototypes of neuromorphic photonic computation units based on chalcogenide phase-change materials. First is a neuromorphic hardware accelerator designed to carry out matrix vector multiplication in convolutional neural networks. Due to the neuromorphic architecture, this prototype can already operate at tera-multiply-accumulate per second speeds. Second is an all-optical spiking neuron, which can serve as a building block for large-scale artificial neural networks. Here, the whole computation is carried out in the optical domain, and the device only needs an electrical interface for data input and readout.
|
| first_indexed | 2024-03-07T07:05:29Z |
| format | Journal article |
| id | oxford-uuid:eee8a648-c0e8-4b7a-bbc6-35404984fd6b |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:05:29Z |
| publishDate | 2021 |
| publisher | American Institute of Physics |
| record_format | dspace |
| spelling | oxford-uuid:eee8a648-c0e8-4b7a-bbc6-35404984fd6b2022-04-21T09:23:04ZChalcogenide phase-change devices for neuromorphic photonic computingJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:eee8a648-c0e8-4b7a-bbc6-35404984fd6bEnglishSymplectic ElementsAmerican Institute of Physics2021Brueckerhoff-Plueckelmann, FFeldmann, JWright, CDBhaskaran, HPernice, WHPThe integration of artificial intelligence systems into daily applications like speech recognition and autonomous driving rapidly increases the amount of data generated and processed. However, satisfying the hardware requirements with the conventional von Neumann architecture remains challenging due to the von Neumann bottleneck. Therefore, new architectures inspired by the working principles of the human brain are developed, and they are called neuromorphic computing. The key principles of neuromorphic computing are in-memory computing to reduce data shuffling and parallelization to decrease computation time. One promising framework for neuromorphic computing is phase-change photonics. By switching to the optical domain, parallelization is inherently possible by wavelength division multiplexing, and high modulation speeds can be deployed. Non-volatile phase-change materials are used to perform multiplications and non-linear operations in an energetically efficient manner. Here, we present two prototypes of neuromorphic photonic computation units based on chalcogenide phase-change materials. First is a neuromorphic hardware accelerator designed to carry out matrix vector multiplication in convolutional neural networks. Due to the neuromorphic architecture, this prototype can already operate at tera-multiply-accumulate per second speeds. Second is an all-optical spiking neuron, which can serve as a building block for large-scale artificial neural networks. Here, the whole computation is carried out in the optical domain, and the device only needs an electrical interface for data input and readout. |
| spellingShingle | Brueckerhoff-Plueckelmann, F Feldmann, J Wright, CD Bhaskaran, H Pernice, WHP Chalcogenide phase-change devices for neuromorphic photonic computing |
| title | Chalcogenide phase-change devices for neuromorphic photonic computing |
| title_full | Chalcogenide phase-change devices for neuromorphic photonic computing |
| title_fullStr | Chalcogenide phase-change devices for neuromorphic photonic computing |
| title_full_unstemmed | Chalcogenide phase-change devices for neuromorphic photonic computing |
| title_short | Chalcogenide phase-change devices for neuromorphic photonic computing |
| title_sort | chalcogenide phase change devices for neuromorphic photonic computing |
| work_keys_str_mv | AT brueckerhoffplueckelmannf chalcogenidephasechangedevicesforneuromorphicphotoniccomputing AT feldmannj chalcogenidephasechangedevicesforneuromorphicphotoniccomputing AT wrightcd chalcogenidephasechangedevicesforneuromorphicphotoniccomputing AT bhaskaranh chalcogenidephasechangedevicesforneuromorphicphotoniccomputing AT pernicewhp chalcogenidephasechangedevicesforneuromorphicphotoniccomputing |