|
|
|
|
LEADER |
01730nam a2200241Ia 4500 |
001 |
10.3390-photonics9040217 |
008 |
220425s2022 CNT 000 0 und d |
020 |
|
|
|a 23046732 (ISSN)
|
245 |
1 |
0 |
|a Multilayer Photonic Spiking Neural Networks: Generalized Supervised Learning Algorithm and Network Optimization
|
260 |
|
0 |
|b MDPI
|c 2022
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.3390/photonics9040217
|
520 |
3 |
|
|a We propose a generalized supervised learning algorithm for multilayer photonic spiking neural networks (SNNs) by combining the spike-timing dependent plasticity (STDP) rule and the gradient descent mechanism. A vertical-cavity surface-emitting laser with an embedded saturable absorber (VCSEL-SA) is employed as a photonic leaky-integrate-and-fire (LIF) neuron. The temporal coding strategy is employed to transform information into the precise firing time. With the modified supervised learning algorithm, the trained multilayer photonic SNN successfully solves the XOR problem and performs well on the Iris and Wisconsin breast cancer datasets. This indicates that a generalized supervised learning algorithm is realized for multilayer photonic SNN. In addition, network optimization is performed by considering different network sizes. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
|
650 |
0 |
4 |
|a multilayer spiking neural network
|
650 |
0 |
4 |
|a photonic spiking neural network
|
650 |
0 |
4 |
|a spike timing dependent plasticity
|
650 |
0 |
4 |
|a supervised learning
|
650 |
0 |
4 |
|a vertical-cavity surface-emitting lasers
|
700 |
1 |
|
|a Fu, C.
|e author
|
700 |
1 |
|
|a Han, Y.
|e author
|
700 |
1 |
|
|a Hao, Y.
|e author
|
700 |
1 |
|
|a Song, Z.
|e author
|
700 |
1 |
|
|a Xiang, S.
|e author
|
773 |
|
|
|t Photonics
|