Brainwave implanted reservoir computing
Source abstract
Abstract
This work aims to build a reservoir computing system to recognize signals with the help of brainwaves as the input signals. The brainwave signals were acquired as the participants were listening to the signals. The human brain in this study can be regarded as the assistant neural networks or non-linear activation function to improve the signal recognition. We showed that within the brainwave frequency ranges from 14 to 16, 20, 30, and 32 Hz, the mean squared errors of the input signal recognition were lower than those without brainwaves. This result has demonstrated that the reservoir computing system with the help of human responses can obtain more precise results.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Neural Networks and Reservoir Computing · Advanced Memory and Neural Computing · Neural dynamics and brain function
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Optics and Photonics, National Central University 1 , No. 300, Zhongda Road, Zhongli District, Taoyuan 320317, Taiwan
Department of Biotechnology and Laboratory Science in Medicine, National Yang Ming Chiao Tung University 2 , No. 155, Sec. 2, Linong Street, Taipei 11221, Taiwan
3 ISIFC Génie Biomédical, Université de Franche-Comté, 23 Rue Alain Savary, 25000 Besançon, France.
Funding
National Science and Technology Council
References (27)
Show source-provided references
1. Impact of coupling topology upon noise robustness of small optical reservoirs10.1038/s41598-020-70775-8 ↗
2. The go files: AI computer wraps up 4-1 victory against human champion10.1038/nature.2016.19575 ↗
3. Application of the deep learning for the prediction of rainfall in Southern Taiwan10.1038/s41598-019-49242-6 ↗
4. All optical XOR logic gate formed by unsupervised optical neuron networks10.1016/j.neucom.2021.07.028 ↗
5. Optical neural networks based on optical fiber-communication system10.1016/j.neucom.2019.07.051 ↗
6. Utilizing optical neural network to establish high-performance OR and XOR logic gates10.1016/j.engappai.2022.105788 ↗
7. Reconfigurable electro-optical logic gates using a 2-layer multilayer perceptron10.1038/s41598-022-18408-0 ↗
8. A hybrid deep neural network for classification of schizophrenia using EEG data10.1038/s41598-021-83350-6 ↗
9. Recent approaches on classification and feature extraction of EEG signal: A review10.1017/s0263574721000382 ↗
10. An adaptive general type-2 fuzzy logic approach for psychophysiological state modeling in real-time human–machine interfaces10.1109/thms.2020.3027531 ↗
11. Progress in brain computer interface: Challenges and opportunities10.3389/fnsys.2021.578875 ↗
12. 2021
13. Physical reservoir computing—An introductory perspective10.35848/1347-4065/ab8d4f ↗
14. Echo state property of neuronal cell cultures
15. Physical reservoir computing with FORCE learning in a living neuronal culture10.1063/5.0064771 ↗
16. Quantification of information processing capacity in living brain as physical reservoir10.1063/5.0152585 ↗
17. Spectral characteristics of EEG during active emotional musical performance10.3390/s21227466 ↗
18. Comparing neural correlates of human emotions across multiple stimulus presentation paradigms10.3390/brainsci11060696 ↗
19. 2019 · 285
20. The ‘echo state’ approach to analysing and training recurrent neural networks
21. The ‘echo state’ approach to analysing and training recurrent neural networks–with an Erratum note
22. Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication10.1126/science.1091277 ↗
23. Design of deep echo state networks10.1016/j.neunet.2018.08.002 ↗
24. Deep echo state network with reservoirs of multiple activation functions for time-series prediction10.1007/s12046-019-1124-y ↗
25. Deep echo state networks with uncertainty quantification for spatio-temporal forecasting10.1002/env.2553 ↗
26. Gamma and beta frequency oscillations in response to novel auditory stimuli: A comparison of human electroencephalogram (EEG) data with in vitro models10.1073/pnas.120162397 ↗
27. Distinctive properties of biological neural networks and recent advances in bottom-up approaches toward a better biologically plausible neural network10.3389/fncom.2023.1092185 ↗