### Abstract

Language | English |
---|---|

Title of host publication | The Fractal geometry of the brain |

Editors | Antonio Di Ieva |

Place of Publication | New York |

Publisher | Springer, Springer Nature |

Pages | 567-580 |

Number of pages | 14 |

ISBN (Print) | 9781493939954 |

DOIs | |

Publication status | Published - 2016 |

### Publication series

Name | Springer Series in Computational Neuroscience |
---|---|

Publisher | Springer |

### Fingerprint

### Keywords

- computational intelligence
- complex systems
- analysis of non-geometric input spaces
- fractal analysis
- brain research

### Cite this

*The Fractal geometry of the brain*(pp. 567-580). (Springer Series in Computational Neuroscience). New York: Springer, Springer Nature. https://doi.org/10.1007/978-1-4939-3995-4_36

}

*The Fractal geometry of the brain.*Springer Series in Computational Neuroscience, Springer, Springer Nature, New York, pp. 567-580. https://doi.org/10.1007/978-1-4939-3995-4_36

**Fractal geometry meets computational intelligence : future perspectives.** / Livi, Lorenzo; Sadeghian, Alireza; Di Ieva, Antonio.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Research › peer-review

TY - CHAP

T1 - Fractal geometry meets computational intelligence

T2 - future perspectives

AU - Livi, Lorenzo

AU - Sadeghian, Alireza

AU - Di Ieva, Antonio

PY - 2016

Y1 - 2016

N2 - Characterizations in terms of fractals are typically employed for systems with complex and multi-scale descriptions. A prominent example of such systems is provided by the human brain, which can be idealized as a complex dynamical system made of many interacting subunits. The human brain can be modeled in terms of observable variables together with their spatio-temporal-functional relations. Computational Intelligence is a research field bridging many nature-inspired computational methods, such as artificial neural networks, fuzzy systems, and evolutionary and swarm intelligence optimization techniques. Typical problems faced by means of Computational Intelligence methods include those of recognition, such as classification and prediction. Although historically conceived to operate in some vector space, such methods have been recently extended to the so-called non-geometric spaces, considering labeled graphs as the most general example of such patterns. Here we suggest that fractal analysis and Computational Intelligence methods can be exploited together in neuroscience research. Fractal characterizations can be used to (i) assess scale-invariant properties and to (ii) offer numeric, feature-based representations to complement the usually more complex pattern structures encountered in neurosciences. Computational Intelligence methods could be used to exploit such fractal characterizations, considering also the possibility to perform data-driven analysis of non-geometric input spaces, hence overcoming the intrinsic limits related to Euclidean geometry.

AB - Characterizations in terms of fractals are typically employed for systems with complex and multi-scale descriptions. A prominent example of such systems is provided by the human brain, which can be idealized as a complex dynamical system made of many interacting subunits. The human brain can be modeled in terms of observable variables together with their spatio-temporal-functional relations. Computational Intelligence is a research field bridging many nature-inspired computational methods, such as artificial neural networks, fuzzy systems, and evolutionary and swarm intelligence optimization techniques. Typical problems faced by means of Computational Intelligence methods include those of recognition, such as classification and prediction. Although historically conceived to operate in some vector space, such methods have been recently extended to the so-called non-geometric spaces, considering labeled graphs as the most general example of such patterns. Here we suggest that fractal analysis and Computational Intelligence methods can be exploited together in neuroscience research. Fractal characterizations can be used to (i) assess scale-invariant properties and to (ii) offer numeric, feature-based representations to complement the usually more complex pattern structures encountered in neurosciences. Computational Intelligence methods could be used to exploit such fractal characterizations, considering also the possibility to perform data-driven analysis of non-geometric input spaces, hence overcoming the intrinsic limits related to Euclidean geometry.

KW - computational intelligence

KW - complex systems

KW - analysis of non-geometric input spaces

KW - fractal analysis

KW - brain research

U2 - 10.1007/978-1-4939-3995-4_36

DO - 10.1007/978-1-4939-3995-4_36

M3 - Chapter

SN - 9781493939954

T3 - Springer Series in Computational Neuroscience

SP - 567

EP - 580

BT - The Fractal geometry of the brain

A2 - Di Ieva, Antonio

PB - Springer, Springer Nature

CY - New York

ER -