Multilayer perceptrons

Research output: Chapter in Book/Report/Conference proceedingEntry for encyclopedia/dictionarypeer-review


This article briefly introduces Artificial Neural Networks for beginners. In its first part, it describes the functioning of a single artificial neuron for simple binary classification tasks. The method is later generalized to single-layer networks, whose functioning is shown on simple multi-class classification tasks. Than, the fact that single-layer Neural Networks may fail to correctly classify non-linearly separable problems is shown by means of a simple example. Finally, multi-layer Neural Networks are presented, as more general methods, able to obtain satisfactory results potentially on any kind of classification problem, including non-linearly separable ones.

Original languageEnglish
Title of host publicationEncyclopedia of Bioinformatics and Computational Biology
Subtitle of host publicationABC of Bioinformatics
EditorsShoba Ranganathan, Michael Gribskov, Kenta Nakai, Christian Schönbach
Number of pages9
ISBN (Electronic)9780128114322
ISBN (Print)9780128114148
Publication statusPublished - 2019


  • Artificial neural networks
  • Multi-layer neural networks
  • Non-linearly separable problems
  • Perceptron
  • Perceptron learning rule


Dive into the research topics of 'Multilayer perceptrons'. Together they form a unique fingerprint.

Cite this