PUBLICATION DATE

2017-02-27

AUTHORS

Jianhua Yang, Min Yao, Tianqi Wu

TITLE

Dolphin Swarm Extreme Learning Machine

ISSUE

2

VOLUME

9

ISSN (print)

1866-9956

ISSN (electronic)

1866-9964

ABSTRACT

As a novel learning algorithm for a single hidden-layer feedforward neural network, the extreme learning machine has attracted much research attention for its fast training speed and good generalization performances. Instead of iteratively tuning the parameters, the extreme machine can be seen as a linear optimization problem by randomly generating the input weights and hidden biases. However, the random determination of the input weights and hidden biases may bring non-optimal parameters, which have a negative impact on the final results or need more hidden nodes for the neural network. To overcome the above drawbacks caused by the non-optimal input weights and hidden biases, we propose a new hybrid learning algorithm named dolphin swarm algorithm extreme learning machine adopting the dolphin swarm algorithm to optimize the input weights and hidden biases efficiently. Each set of input weights and hidden biases is encoded into one vector, namely the dolphin. The dolphins are evaluated by root mean squared error and updated by the four pivotal phases of the dolphin swarm algorithm. Eventually, we will obtain an optimal set of input weights and hidden biases. To evaluate the effectiveness of our method, we compare the proposed algorithm with the standard extreme learning machine and three state-of-the-art methods, which are the particle swarm optimization extreme learning machine, evolutionary extreme learning machine, and self-adaptive evolutionary extreme learning machine, under 13 benchmark datasets obtained from the University of California Irvine Machine Learning Repository. The experimental results demonstrate that the proposed method can achieve superior generalization performances than all the compared algorithms.

How to use: Click on a object to move its position. Double click to open its homepage. Right click to preview its contents.

Download the RDF metadata as:   json-ld nt turtle xml License info


35 TRIPLES      30 PREDICATES      35 URIs      21 LITERALS

Subject Predicate Object
1 articles:4716164b8ed5c64766f96f2391a1aba7 sg:abstract Abstract As a novel learning algorithm for a single hidden-layer feedforward neural network, the extreme learning machine has attracted much research attention for its fast training speed and good generalization performances. Instead of iteratively tuning the parameters, the extreme machine can be seen as a linear optimization problem by randomly generating the input weights and hidden biases. However, the random determination of the input weights and hidden biases may bring non-optimal parameters, which have a negative impact on the final results or need more hidden nodes for the neural network. To overcome the above drawbacks caused by the non-optimal input weights and hidden biases, we propose a new hybrid learning algorithm named dolphin swarm algorithm extreme learning machine adopting the dolphin swarm algorithm to optimize the input weights and hidden biases efficiently. Each set of input weights and hidden biases is encoded into one vector, namely the dolphin. The dolphins are evaluated by root mean squared error and updated by the four pivotal phases of the dolphin swarm algorithm. Eventually, we will obtain an optimal set of input weights and hidden biases. To evaluate the effectiveness of our method, we compare the proposed algorithm with the standard extreme learning machine and three state-of-the-art methods, which are the particle swarm optimization extreme learning machine, evolutionary extreme learning machine, and self-adaptive evolutionary extreme learning machine, under 13 benchmark datasets obtained from the University of California Irvine Machine Learning Repository. The experimental results demonstrate that the proposed method can achieve superior generalization performances than all the compared algorithms.
2 sg:articleType OriginalPaper
3 sg:coverYear 2017
4 sg:coverYearMonth 2017-04
5 sg:ddsId s12559-017-9451-y
6 sg:ddsIdJournalBrand 12559
7 sg:doi 10.1007/s12559-017-9451-y
8 sg:doiLink http://dx.doi.org/10.1007/s12559-017-9451-y
9 sg:hasContributingOrganization grid-institutes:grid.13402.34
10 sg:hasContribution contributions:1dfd0dd537747f6702c615f45bae687a
11 contributions:aeb9a757d01c463343ab0fa2a1621dfb
12 contributions:ddf8c8390aa1ca37843f2076fa2af216
13 sg:hasFieldOfResearchCode anzsrc-for:08
14 anzsrc-for:0801
15 sg:hasJournal journals:8eab5de01e299505ff7bc2ff5004dcc4
16 journals:e533c8f2483d53b2a3660b2c9949490c
17 sg:hasJournalBrand journal-brands:4073449a8eb285a12eda232c532ec199
18 sg:indexingDatabase Scopus
19 Web of Science
20 sg:issnElectronic 1866-9964
21 sg:issnPrint 1866-9956
22 sg:issue 2
23 sg:language English
24 sg:license http://scigraph.springernature.com/explorer/license/
25 sg:pageEnd 284
26 sg:pageStart 275
27 sg:publicationDate 2017-02-27
28 sg:publicationYear 2017
29 sg:publicationYearMonth 2017-02
30 sg:scigraphId 4716164b8ed5c64766f96f2391a1aba7
31 sg:title Dolphin Swarm Extreme Learning Machine
32 sg:volume 9
33 sg:webpage https://link.springer.com/10.1007/s12559-017-9451-y
34 rdf:type sg:Article
35 rdfs:label Article: Dolphin Swarm Extreme Learning Machine
HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular JSON format for linked data.

curl -H 'Accept: application/ld+json' 'http://scigraph.springernature.com/things/articles/4716164b8ed5c64766f96f2391a1aba7'

N-Triples is a line-based linked data format ideal for batch operations .

curl -H 'Accept: application/n-triples' 'http://scigraph.springernature.com/things/articles/4716164b8ed5c64766f96f2391a1aba7'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/articles/4716164b8ed5c64766f96f2391a1aba7'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/articles/4716164b8ed5c64766f96f2391a1aba7'






Preview window. Press ESC to close (or click here)


...