國立虎尾科技大學 |

Language: English

Back

SPAF-network with Saturating Pretrai...

Burhani, Hasham.

SPAF-network with Saturating Pretraining Neurons.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	SPAF-network with Saturating Pretraining Neurons./
Author:	Burhani, Hasham.
Description:	1 online resource (144 pages)
Notes:	Source: Masters Abstracts International, Volume: 55-04.
Subject:	Artificial intelligence. -
Online resource:	click for full text (PQDT)
ISBN:	9781339647159

SPAF-network with Saturating Pretraining Neurons.
Burhani, Hasham.

SPAF-network with Saturating Pretraining Neurons. - 1 online resource (144 pages)

Source: Masters Abstracts International, Volume: 55-04.

Thesis (M.S.)--Trent University (Canada), 2016.

Includes bibliographical references

In this work, various aspects of neural networks, pre-trained with denoising autoencoders (DAE) are explored. To saturate neurons more quickly for feature learning in DAE, an activation function that offers higher gradients is introduced. Moreover, the introduction of sparsity functions applied to the hidden layer representations is studied. More importantly, a technique that swaps the activation functions of fully trained DAE to logistic functions is studied, networks trained using this technique are reffered to as SPAF-networks. For evaluation, the popular MNIST dataset as well as all $3$ sub-datasets of the Chars74k dataset are used for classification purposes. The SPAF-network is also analyzed for the features it learns with a logistic, ReLU and a custom activation function. Lastly future roadmap is proposed for enhancements to the SPAF-network.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781339647159Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

SPAF-network with Saturating Pretraining Neurons.
LDR:01996ntm a2200337K 4500 001 915742
005 20180823122923.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781339647159
035 $a (MiAaPQ)AAI10100845
035 $a (MiAaPQ)trentu:10315
035 $a AAI10100845
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Burhani, Hasham. $3 1189226
245 1 0 $a SPAF-network with Saturating Pretraining Neurons.
264 0 $c 2016
300 $a 1 online resource (144 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 55-04.
500 $a Adviser: Feng Wenying.
502 $a Thesis (M.S.)--Trent University (Canada), 2016.
504 $a Includes bibliographical references
520 $a In this work, various aspects of neural networks, pre-trained with denoising autoencoders (DAE) are explored. To saturate neurons more quickly for feature learning in DAE, an activation function that offers higher gradients is introduced. Moreover, the introduction of sparsity functions applied to the hidden layer representations is studied. More importantly, a technique that swaps the activation functions of fully trained DAE to logistic functions is studied, networks trained using this technique are reffered to as SPAF-networks. For evaluation, the popular MNIST dataset as well as all $3$ sub-datasets of the Chars74k dataset are used for classification purposes. The SPAF-network is also analyzed for the features it learns with a logistic, ReLU and a custom activation function. Lastly future roadmap is proposed for enhancements to the SPAF-network.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer science. $3 573171
650 4 $a Mathematics. $3 527692
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
690 $a 0405
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Trent University (Canada). $b Applied Modeling and Quantitative Methods. $3 1189227
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10100845 $z click for full text (PQDT)

based on 0 review(s)

Multimedia

Reviews

Add a review and share your thoughts with other readers

Export

pickup library