Modular Neural Networks

  • Patricia Melin
  • Oscar Castillo
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 172)


We describe in this chapter the basic concepts, theory and algorithms of modular and ensemble neural networks. We will also give particular attention to the problem of response integration, which is very important because response integration is responsible for combining all the outputs of the modules. Basically, a modular or ensemble neural network uses several monolithic neural networks to solve a specific problem. The basic idea is that combining the results of several simple neural networks we will achieve a better overall result in terms of accuracy and also learning can be done faster. For pattern recognition problems, which have great complexity and are defined over high dimensional spaces, modular neural networks are a great alternative for achieving the level of accuracy and efficiency needed for real-time applications. This chapter will serve as a basis for the modular architectures that will be proposed in later chapters for specific pattern recognition problems.


Neural Network Fuzzy Measure Response Integration Pattern Recognition Problem Ensemble Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Authors and Affiliations

  • Patricia Melin
    • 1
  • Oscar Castillo
    • 2
  1. 1.Department of Computer ScienceTijuana Institute of TechnologyChula VistaUSA
  2. 2.Department of Computer ScienceTijuana Institute of TechnologyChula VistaUSA

Personalised recommendations