Autonomous learning machine for online big data analysis
Deep Metric Learning (DML) supports the non-linearity problem faced when unsupervised learning is used; whereby multi-input data corresponds to one output. Hence, DML is suitable for managing large imbalanced datasets which are often faced in the production industry in which a handful of defective p...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156447 |
| _version_ | 1824454991937536000 |
|---|---|
| author | Ng, Jia Yu |
| author2 | Mahardhika Pratama |
| author_facet | Mahardhika Pratama Ng, Jia Yu |
| author_sort | Ng, Jia Yu |
| collection | NTU |
| description | Deep Metric Learning (DML) supports the non-linearity problem faced when unsupervised learning is used; whereby multi-input data corresponds to one output. Hence, DML is suitable for managing large imbalanced datasets which are often faced in the production industry in which a handful of defective products were manufactured. One of the methods used in DML is the autoencoders. The use of autoencoder information can be utilized in overcoming the convergence problem which arises when random samples are used for model training [1]. Two separate autoencoders were trained for normal products and defective products respectively. Next, the Triplet network is trained to learn an embedding of the feature vector representation of the products. The embedding prevents the convergence problem by moving each sample closer to its reconstruction restored with the same class’s autoencoder and further from the opposite class’s autoencoder [1]. Eventually, it allocates each sample to the associated autoencoder’s class, which recovers the sample’s nearest reconstruction in the embedding space. |
| first_indexed | 2025-02-19T03:31:07Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/156447 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:31:07Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1564472022-04-16T14:20:51Z Autonomous learning machine for online big data analysis Ng, Jia Yu Mahardhika Pratama Zhang Jie School of Computer Science and Engineering ZhangJ@ntu.edu.sg, mpratama@ntu.edu.sg Engineering::Computer science and engineering Deep Metric Learning (DML) supports the non-linearity problem faced when unsupervised learning is used; whereby multi-input data corresponds to one output. Hence, DML is suitable for managing large imbalanced datasets which are often faced in the production industry in which a handful of defective products were manufactured. One of the methods used in DML is the autoencoders. The use of autoencoder information can be utilized in overcoming the convergence problem which arises when random samples are used for model training [1]. Two separate autoencoders were trained for normal products and defective products respectively. Next, the Triplet network is trained to learn an embedding of the feature vector representation of the products. The embedding prevents the convergence problem by moving each sample closer to its reconstruction restored with the same class’s autoencoder and further from the opposite class’s autoencoder [1]. Eventually, it allocates each sample to the associated autoencoder’s class, which recovers the sample’s nearest reconstruction in the embedding space. Bachelor of Engineering (Computer Science) 2022-04-16T14:20:16Z 2022-04-16T14:20:16Z 2022 Final Year Project (FYP) Ng, J. Y. (2022). Autonomous learning machine for online big data analysis. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156447 https://hdl.handle.net/10356/156447 en SCSE21-0291 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Ng, Jia Yu Autonomous learning machine for online big data analysis |
| title | Autonomous learning machine for online big data analysis |
| title_full | Autonomous learning machine for online big data analysis |
| title_fullStr | Autonomous learning machine for online big data analysis |
| title_full_unstemmed | Autonomous learning machine for online big data analysis |
| title_short | Autonomous learning machine for online big data analysis |
| title_sort | autonomous learning machine for online big data analysis |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/156447 |
| work_keys_str_mv | AT ngjiayu autonomouslearningmachineforonlinebigdataanalysis |