All-optical spiking neurosynaptic networks with self-learning capabilities
Software implementations of brain-inspired computing underlie many important computational tasks, from image processing to speech recognition, artificial intelligence and deep learning applications. Yet, unlike real neural tissue, traditional computing architectures physically separate the core comp...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Published: |
Nature Research
2019
|
| _version_ | 1826282491046002688 |
|---|---|
| author | Feldmann, J Youngblood, N Wright, C Bhaskaran, H Pernice, W |
| author_facet | Feldmann, J Youngblood, N Wright, C Bhaskaran, H Pernice, W |
| author_sort | Feldmann, J |
| collection | OXFORD |
| description | Software implementations of brain-inspired computing underlie many important computational tasks, from image processing to speech recognition, artificial intelligence and deep learning applications. Yet, unlike real neural tissue, traditional computing architectures physically separate the core computing functions of memory and processing, making fast, efficient and low-energy computing difficult to achieve. To overcome such limitations, an attractive alternative is to design hardware that mimics neurons and synapses. Such hardware, when connected in networks or neuromorphic systems, processes information in a way more analogous to brains. Here we present an all-optical version of such a neurosynaptic system, capable of supervised and unsupervised learning. We exploit wavelength division multiplexing techniques to implement a scalable circuit architecture for photonic neural networks, successfully demonstrating pattern recognition directly in the optical domain. Such photonic neurosynaptic networks promise access to the high speed and high bandwidth inherent to optical systems, thus enabling the direct processing of optical telecommunication and visual data. |
| first_indexed | 2024-03-07T00:44:39Z |
| format | Journal article |
| id | oxford-uuid:843190f3-e460-499e-b230-63b8bc349502 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T00:44:39Z |
| publishDate | 2019 |
| publisher | Nature Research |
| record_format | dspace |
| spelling | oxford-uuid:843190f3-e460-499e-b230-63b8bc3495022022-03-26T21:49:38ZAll-optical spiking neurosynaptic networks with self-learning capabilitiesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:843190f3-e460-499e-b230-63b8bc349502Symplectic Elements at OxfordNature Research2019Feldmann, JYoungblood, NWright, CBhaskaran, HPernice, WSoftware implementations of brain-inspired computing underlie many important computational tasks, from image processing to speech recognition, artificial intelligence and deep learning applications. Yet, unlike real neural tissue, traditional computing architectures physically separate the core computing functions of memory and processing, making fast, efficient and low-energy computing difficult to achieve. To overcome such limitations, an attractive alternative is to design hardware that mimics neurons and synapses. Such hardware, when connected in networks or neuromorphic systems, processes information in a way more analogous to brains. Here we present an all-optical version of such a neurosynaptic system, capable of supervised and unsupervised learning. We exploit wavelength division multiplexing techniques to implement a scalable circuit architecture for photonic neural networks, successfully demonstrating pattern recognition directly in the optical domain. Such photonic neurosynaptic networks promise access to the high speed and high bandwidth inherent to optical systems, thus enabling the direct processing of optical telecommunication and visual data. |
| spellingShingle | Feldmann, J Youngblood, N Wright, C Bhaskaran, H Pernice, W All-optical spiking neurosynaptic networks with self-learning capabilities |
| title | All-optical spiking neurosynaptic networks with self-learning capabilities |
| title_full | All-optical spiking neurosynaptic networks with self-learning capabilities |
| title_fullStr | All-optical spiking neurosynaptic networks with self-learning capabilities |
| title_full_unstemmed | All-optical spiking neurosynaptic networks with self-learning capabilities |
| title_short | All-optical spiking neurosynaptic networks with self-learning capabilities |
| title_sort | all optical spiking neurosynaptic networks with self learning capabilities |
| work_keys_str_mv | AT feldmannj allopticalspikingneurosynapticnetworkswithselflearningcapabilities AT youngbloodn allopticalspikingneurosynapticnetworkswithselflearningcapabilities AT wrightc allopticalspikingneurosynapticnetworkswithselflearningcapabilities AT bhaskaranh allopticalspikingneurosynapticnetworkswithselflearningcapabilities AT pernicew allopticalspikingneurosynapticnetworkswithselflearningcapabilities |