Abstract
In this chapter, we will provide the general and fundamental background related to two types of artificial neural networks techniques: spiking neural networks (SNN) and dendrite morphological neural networks (DMNN). The third generation of artificial neural networks, also known as SNN, has shown to be a very promising tool for the recognition of patterns due to the inclusion of time-space information analysis. On the other hand, DMNN models provide advantages over traditional neural network models; the main advantage is the implementation of closed decision limits. In this chapter, we show a brief study of the most recent advances related to SNN and DMNN. We explain the basic knowledge concerning this type of neural models, as well as their application in simple examples of biosignal analysis for their understanding. In the end, we make a series of conclusions and proposals for future research.
Original language | English |
---|---|
Title of host publication | Biosignal Processing and Classification Using Computational Learning and Intelligence |
Subtitle of host publication | Principles, Algorithms, and Applications |
Publisher | Elsevier |
Pages | 197-224 |
Number of pages | 28 |
ISBN (Electronic) | 9780128201251 |
DOIs | |
State | Published - 1 Jan 2021 |
Keywords
- Dendrite morphological neural networks
- Neural networks
- Spiking neural networks
- Time-space information