Standard

Bio-inspired machine learning: programmed death and replication. / Грабовский, Андрей Владимирович; Vanchurin, Vitaly.

In: Neural Computing and Applications, Vol. 35, No. 27, 09.2023, p. 20273-20298.

Research output: Contribution to journal › Article › peer-review

Harvard

Грабовский, АВ & Vanchurin, V 2023, 'Bio-inspired machine learning: programmed death and replication', Neural Computing and Applications, vol. 35, no. 27, pp. 20273-20298. https://doi.org/10.1007/s00521-023-08806-4

APA

Грабовский, А. В., & Vanchurin, V. (2023). Bio-inspired machine learning: programmed death and replication. Neural Computing and Applications, 35(27), 20273-20298. https://doi.org/10.1007/s00521-023-08806-4

Vancouver

Грабовский АВ, Vanchurin V. Bio-inspired machine learning: programmed death and replication. Neural Computing and Applications. 2023 Sept;35(27):20273-20298. doi: 10.1007/s00521-023-08806-4

Author

Грабовский, Андрей Владимирович ; Vanchurin, Vitaly. / Bio-inspired machine learning: programmed death and replication. In: Neural Computing and Applications. 2023 ; Vol. 35, No. 27. pp. 20273-20298.

BibTeX

@article{abceaad2b93e42af82505161a0d233a4,
title = "Bio-inspired machine learning: programmed death and replication",
abstract = "We analyze algorithmic and computational aspects of biological phenomena, such as replication and programmed death, in the context of machine learning. We use two different measures of neuron efficiency to develop machine learning algorithms for adding neurons to the system (i.e., replication algorithm) and removing neurons from the system (i.e., programmed death algorithm). We argue that the programmed death algorithm can be used for compression of neural networks and the replication algorithm can be used for improving performance of the already trained neural networks. We also show that a combined algorithm of programmed death and replication can improve the learning efficiency of arbitrary machine learning systems. The computational advantages of the bio-inspired algorithms are demonstrated by training feedforward neural networks on the MNIST dataset of handwritten images.",
keywords = "Bio-inspired algorithms, Classification, Constructive algorithms, Machine learning, Neural networks, Neuron correlations, Pruning algorithms",
author = "Грабовский, {Андрей Владимирович} and Vitaly Vanchurin",
note = "V.V. was supported in part by the Foundational Questions Institute (FQXi) and the Oak Ridge Institute for Science and Education (ORISE).",
year = "2023",
month = sep,
doi = "10.1007/s00521-023-08806-4",
language = "English",
volume = "35",
pages = "20273--20298",
journal = "Neural Computing and Applications",
issn = "1433-3058",
publisher = "Springer London",
number = "27",

}

RIS

TY - JOUR

T1 - Bio-inspired machine learning: programmed death and replication

AU - Грабовский, Андрей Владимирович

AU - Vanchurin, Vitaly

N1 - V.V. was supported in part by the Foundational Questions Institute (FQXi) and the Oak Ridge Institute for Science and Education (ORISE).

PY - 2023/9

Y1 - 2023/9

N2 - We analyze algorithmic and computational aspects of biological phenomena, such as replication and programmed death, in the context of machine learning. We use two different measures of neuron efficiency to develop machine learning algorithms for adding neurons to the system (i.e., replication algorithm) and removing neurons from the system (i.e., programmed death algorithm). We argue that the programmed death algorithm can be used for compression of neural networks and the replication algorithm can be used for improving performance of the already trained neural networks. We also show that a combined algorithm of programmed death and replication can improve the learning efficiency of arbitrary machine learning systems. The computational advantages of the bio-inspired algorithms are demonstrated by training feedforward neural networks on the MNIST dataset of handwritten images.

AB - We analyze algorithmic and computational aspects of biological phenomena, such as replication and programmed death, in the context of machine learning. We use two different measures of neuron efficiency to develop machine learning algorithms for adding neurons to the system (i.e., replication algorithm) and removing neurons from the system (i.e., programmed death algorithm). We argue that the programmed death algorithm can be used for compression of neural networks and the replication algorithm can be used for improving performance of the already trained neural networks. We also show that a combined algorithm of programmed death and replication can improve the learning efficiency of arbitrary machine learning systems. The computational advantages of the bio-inspired algorithms are demonstrated by training feedforward neural networks on the MNIST dataset of handwritten images.

KW - Bio-inspired algorithms

KW - Classification

KW - Constructive algorithms

KW - Machine learning

KW - Neural networks

KW - Neuron correlations

KW - Pruning algorithms

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85165286519&origin=inward&txGid=33fc24869a8dbc1ac624f533115995fe

UR - https://www.mendeley.com/catalogue/2f2fb520-2830-3781-a865-4f82b90b6f8b/

U2 - 10.1007/s00521-023-08806-4

DO - 10.1007/s00521-023-08806-4

M3 - Article

VL - 35

SP - 20273

EP - 20298

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 1433-3058

IS - 27

ER -

ID: 52756398