EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Probabilistic Classification Method of Spiking Neural Network Based on Multi-Labeling of Neurons

Mingyu Sung, Jaesoo Kim, Jae-Mo Kang

Mathematics · 02.03.2023 · 11 (5) · 1224

DOI: 10.3390/math11051224 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 02.03.2023. Verfasst von Mingyu Sung und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, deep learning has exhibited outstanding performance in various fields. Even though artificial intelligence achieves excellent performance, the amount of energy required for computations has increased with its development. Hence, the need for a new energy-efficient computer architecture has emerged, which further leads us to the neuromorphic computer. Although neuromorphic computing exhibits several advantages, such as low-power parallelism, it exhibits lower accuracy than deep learning. Therefore, the major challenge is to improve the accuracy while maintaining the neuromorphic computing-specific energy efficiency. In this paper, we propose a novel method of the inference process that considers the probability that after completing the learning process, a neuron can react to multiple target labels. Our proposed method can achieve improved accuracy while maintaining the hardware-friendly, low-power-parallel processing characteristics of a neuromorphic processor. Furthermore, this method converts the spike counts occurring in the learning process into probabilities. The inference process is conducted to implement the interaction between neurons by considering all the spikes that occur. The inferring circuit is expected to show a significant reduction in hardware cost and can afford an algorithm exhibiting a competitive computing performance.

Förderung

  • Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education
  • National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT)

Zitieren

APA

Sung, M., Kim, J., & Kang, J. (2023). Probabilistic Classification Method of Spiking Neural Network Based on Multi-Labeling of Neurons. Mathematics, 11(5), 1224. https://doi.org/10.3390/math11051224

Vancouver

Sung M, Kim J, Kang J. Probabilistic Classification Method of Spiking Neural Network Based on Multi-Labeling of Neurons. Mathematics. 2023;11(5):1224. doi:10.3390/math11051224

BibTeX
@article{Sung2023,
  author = {Sung, Mingyu and Kim, Jaesoo and Kang, Jae-Mo},
  title = {Probabilistic Classification Method of Spiking Neural Network Based on Multi-Labeling of Neurons},
  journal = {Mathematics},
  year = {2023},
  volume = {11},
  number = {5},
  pages = {1224},
  doi = {10.3390/math11051224}
}
Kostenlos starten →