Artificial nanophotonic neuron with internal memory for biologically inspired and reservoir network computing
(2023) In Neuromorphic Computing and Engineering 3(3).- Abstract
Neurons with internal memory have been proposed for biological and bio-inspired neural networks, adding important functionality. We introduce an internal time-limited charge-based memory into a III-V nanowire (NW) based optoelectronic neural node circuit designed for handling optical signals in a neural network. The new circuit can receive inhibiting and exciting light signals, store them, perform a non-linear evaluation, and emit a light signal. Using experimental values from the performance of individual III-V NWs we create a realistic computational model of the complete artificial neural node circuit. We then create a flexible neural network simulation that uses these circuits as neuronal nodes and light for communication between the... (More)
Neurons with internal memory have been proposed for biological and bio-inspired neural networks, adding important functionality. We introduce an internal time-limited charge-based memory into a III-V nanowire (NW) based optoelectronic neural node circuit designed for handling optical signals in a neural network. The new circuit can receive inhibiting and exciting light signals, store them, perform a non-linear evaluation, and emit a light signal. Using experimental values from the performance of individual III-V NWs we create a realistic computational model of the complete artificial neural node circuit. We then create a flexible neural network simulation that uses these circuits as neuronal nodes and light for communication between the nodes. This model can simulate combinations of nodes with different hardware derived memory properties and variable interconnects. Using the full model, we simulate the hardware implementation for two types of neural networks. First, we show that intentional variations in the memory decay time of the nodes can significantly improve the performance of a reservoir network. Second, we simulate the implementation in an anatomically constrained functioning model of the central complex network of the insect brain and find that it resolves an important functionality of the network even with significant variations in the node performance. Our work demonstrates the advantages of an internal memory in a concrete, nanophotonic neural node. The use of variable memory time constants in neural nodes is a general hardware derived feature and could be used in a broad range of implementations.
(Less)
- author
- Winge, David LU ; Borgström, Magnus LU ; Lind, Erik LU and Mikkelsen, Anders LU
- organization
-
- LU Profile Area: Light and Materials
- NanoLund: Centre for Nanoscience
- Synchrotron Radiation Research
- LTH Profile Area: Nanoscience and Semiconductor Technology
- Solid State Physics
- LTH Profile Area: AI and Digitalization
- Nano Electronics (research group)
- Chemical Physics
- LTH Profile Area: Photon Science and Technology
- publishing date
- 2023-09-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- III-V, nanophotonic, nanowires, optoelectronics
- in
- Neuromorphic Computing and Engineering
- volume
- 3
- issue
- 3
- article number
- 034011
- publisher
- IOP Publishing
- external identifiers
-
- scopus:85173248607
- ISSN
- 2634-4386
- DOI
- 10.1088/2634-4386/acf684
- language
- English
- LU publication?
- yes
- id
- 3b3c3e7e-10c4-4d85-938f-f4d24cac8de6
- date added to LUP
- 2023-12-11 14:18:04
- date last changed
- 2024-01-31 10:40:53
@article{3b3c3e7e-10c4-4d85-938f-f4d24cac8de6,
abstract = {{<p>Neurons with internal memory have been proposed for biological and bio-inspired neural networks, adding important functionality. We introduce an internal time-limited charge-based memory into a III-V nanowire (NW) based optoelectronic neural node circuit designed for handling optical signals in a neural network. The new circuit can receive inhibiting and exciting light signals, store them, perform a non-linear evaluation, and emit a light signal. Using experimental values from the performance of individual III-V NWs we create a realistic computational model of the complete artificial neural node circuit. We then create a flexible neural network simulation that uses these circuits as neuronal nodes and light for communication between the nodes. This model can simulate combinations of nodes with different hardware derived memory properties and variable interconnects. Using the full model, we simulate the hardware implementation for two types of neural networks. First, we show that intentional variations in the memory decay time of the nodes can significantly improve the performance of a reservoir network. Second, we simulate the implementation in an anatomically constrained functioning model of the central complex network of the insect brain and find that it resolves an important functionality of the network even with significant variations in the node performance. Our work demonstrates the advantages of an internal memory in a concrete, nanophotonic neural node. The use of variable memory time constants in neural nodes is a general hardware derived feature and could be used in a broad range of implementations.</p>}},
author = {{Winge, David and Borgström, Magnus and Lind, Erik and Mikkelsen, Anders}},
issn = {{2634-4386}},
keywords = {{III-V; nanophotonic; nanowires; optoelectronics}},
language = {{eng}},
month = {{09}},
number = {{3}},
publisher = {{IOP Publishing}},
series = {{Neuromorphic Computing and Engineering}},
title = {{Artificial nanophotonic neuron with internal memory for biologically inspired and reservoir network computing}},
url = {{http://dx.doi.org/10.1088/2634-4386/acf684}},
doi = {{10.1088/2634-4386/acf684}},
volume = {{3}},
year = {{2023}},
}