| Author: | Fan, Jianing |
| Title: | Evaluation of neural network running on Spark |
| Advisors: | Lo, Eric (COMP) |
| Degree: | M.Sc. |
| Year: | 2015 |
| Subject: | Neural networks (Computer science) Back propagation (Artificial intelligence) Machine learning Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Computing |
| Pages: | viii, 84 leaves : illustrations ; 30 cm |
| Language: | English |
| Abstract: | Big data is an unstoppable trend in the era of information, which opens up a new door to understand the world and make decision. Digging up useful knowledge and information from massive data is applied by artificial intelligent technologies such as machine learning, data mining and natural language processing. As the main tool for analysis of big data, machine learning speeds up the development of big data. Neural network algorithm is a type of machine learning algorithm for classification and pattern recognition. Among a variety of neural network algorithms proposed, backpropagation neural network is the most widely used so far. Apache Spark is a young big data analytical platform like Hadoop. It provides users with not only amazing performance but also easy-to-use programming interface and powerful machine learning library. No formal study has assessed the performance of neural network algorithm running on Spark platform so far. Accordingly, we evaluate Spark by implementing backpropagation neural network algorithm on it. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b27800258.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.34 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/200/7845