COPYRIGHT YEAR

2015

AUTHORS

Samad Ahmadi, Arlene Casey, Hossein Ghodrati Noushahr

TITLE

Fast Handwritten Digit Recognition with Multilayer Ensemble Extreme Learning Machine

ABSTRACT

Conventional artificial neural networks and convolutional neural networks perform well on the task of automatic handwriting recognition. But, they suffer from long training times and their complex nature. An alternative learning algorithm called Extreme Learning Machine overcomes these shortcomings by determining the weights of a neural network analytically. In this paper, a novel classifier based on Extreme Learning Machine is proposed that achieves competitive accuracy results while keeping training times low. This classifier is called multilayer ensemble Extreme Learning Machine. The novel classifier is evaluated against traditional backpropagation and Extreme Learning Machine on the well-known MNIST dataset. Possible future work on parallel Extreme Learning Machine is shown up.

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


25 TRIPLES      23 PREDICATES      22 URIs      13 LITERALS

Subject Predicate Object
1 book-chapters:0d8cd0f23f90b19e36f1a8ce6be7e5d6 sg:abstract Abstract Conventional artificial neural networks and convolutional neural networks perform well on the task of automatic handwriting recognition. But, they suffer from long training times and their complex nature. An alternative learning algorithm called Extreme Learning Machine overcomes these shortcomings by determining the weights of a neural network analytically. In this paper, a novel classifier based on Extreme Learning Machine is proposed that achieves competitive accuracy results while keeping training times low. This classifier is called multilayer ensemble Extreme Learning Machine. The novel classifier is evaluated against traditional backpropagation and Extreme Learning Machine on the well-known MNIST dataset. Possible future work on parallel Extreme Learning Machine is shown up.
2 sg:abstractRights OpenAccess
3 sg:bibliographyRights Restricted
4 sg:bodyHtmlRights Restricted
5 sg:bodyPdfRights Restricted
6 sg:copyrightHolder Springer International Publishing Switzerland
7 sg:copyrightYear 2015
8 sg:ddsId Chap5
9 sg:doi 10.1007/978-3-319-25032-8_5
10 sg:esmRights OpenAccess
11 sg:hasBook books:ea2ad207ea83ee0fe768cfb9e8a6898b
12 sg:hasBookEdition book-editions:0cacfb30f91df64b146df73ee9d87cb9
13 sg:hasContribution contributions:6d1ebd5403d5349ae00179209a3985b8
14 contributions:6ed650467946483c87677bce272f738f
15 contributions:994946cfa54266e700700622ef1e5066
16 sg:language En
17 sg:license http://scigraph.springernature.com/explorer/license/
18 sg:metadataRights OpenAccess
19 sg:pageFirst 77
20 sg:pageLast 89
21 sg:scigraphId 0d8cd0f23f90b19e36f1a8ce6be7e5d6
22 sg:title Fast Handwritten Digit Recognition with Multilayer Ensemble Extreme Learning Machine
23 sg:webpage https://link.springer.com/10.1007/978-3-319-25032-8_5
24 rdf:type sg:BookChapter
25 rdfs:label BookChapter: Fast Handwritten Digit Recognition with Multilayer Ensemble 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/book-chapters/0d8cd0f23f90b19e36f1a8ce6be7e5d6'

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

curl -H 'Accept: application/n-triples' 'http://scigraph.springernature.com/things/book-chapters/0d8cd0f23f90b19e36f1a8ce6be7e5d6'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/book-chapters/0d8cd0f23f90b19e36f1a8ce6be7e5d6'

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

curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/book-chapters/0d8cd0f23f90b19e36f1a8ce6be7e5d6'






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


...