Self-organizing maps with dynamic learning for signal reconstruction

Jeongho Cho, António R.C. Paiva, Sung Phil Kim, Justin C. Sanchez, José C. Príncipe

Research output: Contribution to journalArticle

11 Scopus citations

Abstract

Wireless Brain Machine Interface (BMI) communication protocols are faced with the challenge of transmitting the activity of hundreds of neurons which requires large bandwidth. Previously a data compression scheme for neural activity was introduced based on Self Organizing Maps (SOM). In this paper we propose a dynamic learning rule for improved training of the SOM on signals with sparse events which allows for more representative prototype vectors to be found, and consequently better signal reconstruction. This work was developed with BMI applications in mind and therefore our examples are geared towards this type of signals. The simulation results show that the proposed strategy outperforms conventional vector quantization methods for spike reconstruction.

Original languageEnglish (US)
Pages (from-to)274-284
Number of pages11
JournalNeural Networks
Volume20
Issue number2
DOIs
StatePublished - Mar 1 2007

Keywords

  • Brain-machine interface
  • Self-organizing map
  • Spike reconstruction
  • Vector quantization

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Fingerprint Dive into the research topics of 'Self-organizing maps with dynamic learning for signal reconstruction'. Together they form a unique fingerprint.

  • Cite this

    Cho, J., Paiva, A. R. C., Kim, S. P., Sanchez, J. C., & Príncipe, J. C. (2007). Self-organizing maps with dynamic learning for signal reconstruction. Neural Networks, 20(2), 274-284. https://doi.org/10.1016/j.neunet.2006.12.002