Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.contributor.advisor | Shiu, Chi Keung Simon (COMP) | - |
| dc.creator | Lai, King Hon | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/8857 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Design and implementation of pattern recognition system : a convolutional neural network approach | en_US |
| dcterms.abstract | With the success of convolutional neural network models towards problems of image classification. There is a need to investigate deeper in this area. Actual implementation of usable CNNs just came out for few years. As a young topic in machine learning area, there are rooms for improvement in both algorithms and structures. CNN is known for great risk on suffering from over fitting which affects the performance of the product. This dissertation is providing suggestions to model hierarchy and algorithm choices by conduction tests on different hyperparameters of the model. The result is impressive mostly in the concluded rules. Implementation using those rules was able to produce model structure hierarchy by the increase of accuracy, potential by suppressing over fitting problem and consumes less time in training. In particular cases, we see over 33% increase with less training time. The results showed the value of investigation, the product of the dissertation can be applied to other models and different problems. | en_US |
| dcterms.extent | ix, 63, 5 pages : illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2017 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Machine learning. | en_US |
| dcterms.LCSH | Neural networks (Computer science) | en_US |
| dcterms.LCSH | Pattern recognition systems. | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b29500175.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.7 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/8857