國立虎尾科技大學 |

Hyperparameter Optimization of Deep Convolutional Neural Networks Architectures for Object Recognition.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Hyperparameter Optimization of Deep Convolutional Neural Networks Architectures for Object Recognition./
Author:	Albelwi, Saleh.
Description:	1 online resource (105 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-07(E), Section: B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9780355777864

Hyperparameter Optimization of Deep Convolutional Neural Networks Architectures for Object Recognition.
Albelwi, Saleh.

Hyperparameter Optimization of Deep Convolutional Neural Networks Architectures for Object Recognition. - 1 online resource (105 pages)

Source: Dissertation Abstracts International, Volume: 79-07(E), Section: B.

Thesis (Ph.D.)--University of Bridgeport, 2018.

Includes bibliographical references

Recent advances in Convolutional Neural Networks (CNNs) have obtained promising results in difficult deep learning tasks. However, the success of a CNN depends on finding an architecture to fit a given problem. A hand-crafted architecture is a challenging, time-consuming process that requires expert knowledge and effort, due to a large number of architectural design choices. In this dissertation, we present an efficient framework that automatically designs a high-performing CNN architecture for a given problem. In this framework, we introduce a new optimization objective function that combines the error rate and the information learnt by a set of feature maps using deconvolutional networks (deconvnet). The new objective function allows the hyperparameters of the CNN architecture to be optimized in a way that enhances the performance by guiding the CNN through better visualization of learnt features via deconvnet. The actual optimization of the objective function is carried out via the Nelder-Mead Method (NMM). Further, our new objective function results in much faster convergence towards a better architecture. The proposed framework has the ability to explore a CNN architecture's numerous design choices in an efficient way and also allows effective, distributed execution and synchronization via web services. Empirically, we demonstrate that the CNN architecture designed with our approach outperforms several existing approaches in terms of its error rate. Our results are also competitive with state-of-the-art results on the MNIST dataset and perform reasonably against the state-of-the-art results on CIFAR-10 and CIFAR-100 datasets. Our approach has a significant role in increasing the depth, reducing the size of strides, and constraining some convolutional layers not followed by pooling layers in order to find a CNN architecture that produces a high recognition performance.

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

Mode of access: World Wide Web

ISBN: 9780355777864Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Hyperparameter Optimization of Deep Convolutional Neural Networks Architectures for Object Recognition.
LDR:03666ntm a2200325K 4500 001 912202
005 20180608102941.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780355777864
035 $a (MiAaPQ)AAI10748458
035 $a (MiAaPQ)bridgeport:10051
035 $a AAI10748458
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Albelwi, Saleh. $3 1184453
245 1 0 $a Hyperparameter Optimization of Deep Convolutional Neural Networks Architectures for Object Recognition.
264 0 $c 2018
300 $a 1 online resource (105 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: Dissertation Abstracts International, Volume: 79-07(E), Section: B.
500 $a Adviser: Ausif Mahmood.
502 $a Thesis (Ph.D.)--University of Bridgeport, 2018.
504 $a Includes bibliographical references
520 $a Recent advances in Convolutional Neural Networks (CNNs) have obtained promising results in difficult deep learning tasks. However, the success of a CNN depends on finding an architecture to fit a given problem. A hand-crafted architecture is a challenging, time-consuming process that requires expert knowledge and effort, due to a large number of architectural design choices. In this dissertation, we present an efficient framework that automatically designs a high-performing CNN architecture for a given problem. In this framework, we introduce a new optimization objective function that combines the error rate and the information learnt by a set of feature maps using deconvolutional networks (deconvnet). The new objective function allows the hyperparameters of the CNN architecture to be optimized in a way that enhances the performance by guiding the CNN through better visualization of learnt features via deconvnet. The actual optimization of the objective function is carried out via the Nelder-Mead Method (NMM). Further, our new objective function results in much faster convergence towards a better architecture. The proposed framework has the ability to explore a CNN architecture's numerous design choices in an efficient way and also allows effective, distributed execution and synchronization via web services. Empirically, we demonstrate that the CNN architecture designed with our approach outperforms several existing approaches in terms of its error rate. Our results are also competitive with state-of-the-art results on the MNIST dataset and perform reasonably against the state-of-the-art results on CIFAR-10 and CIFAR-100 datasets. Our approach has a significant role in increasing the depth, reducing the size of strides, and constraining some convolutional layers not followed by pooling layers in order to find a CNN architecture that produces a high recognition performance.
520 $a Moreover, we evaluate the effectiveness of reducing the size of the training set on CNNs using a variety of instance selection methods to speed up the training time. We then study how these methods impact classification accuracy. Many instance selection methods require a long run-time to obtain a subset of the representative dataset, especially if the training set is large and has a high dimensionality. One example of these algorithms is Random Mutation Hill Climbing (RMHC). We improve RMHC so that it performs faster than the original algorithm with the same accuracy.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Bridgeport. $b Computer Science and Engineering. $3 1183815
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10748458 $z click for full text (PQDT)