Please use this identifier to cite or link to this item:
https://knowledgecommons.lakeheadu.ca/handle/2453/4673
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yang, Yimin | - |
dc.contributor.author | Paul, Adhri Nandini | - |
dc.date.accessioned | 2020-07-07T16:49:35Z | - |
dc.date.available | 2020-07-07T16:49:35Z | - |
dc.date.created | 2020 | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://knowledgecommons.lakeheadu.ca/handle/2453/4673 | - |
dc.description.abstract | Network aims to optimize for minimizing the cost function and provide better performance. This experimental optimization procedure is widely recognized as gradient descent, which is a form of iterative learning that starts from a random point on a function and travels down its slope, in steps, until it reaches to the steepest point which is time-consuming and slow to converge. Over the last couple of decades, several variations of the non-iterative neural network training algorithms have been proposed, such as Random Forest and Quicknet. However, the non-iterative neural network training algorithms do not support online training that given a very largesized training data, one needs enormous computing resources to train neural network. In this thesis, a non-iterative learning strategy with online sequential has been exploited. In Chapter 3, a single layer Online Sequential Sub-Network node (OS-SN) classifier has been proposed that can provide competitive accuracy by pulling the residual network error and feeding it back into hidden layers. In Chapter 4, a multilayer network is proposed where the first portion built by transforming multi-layer autoencoder into an Online Sequential Auto-Encoder(OS-AE) and use OS-SN for classification. In Chapter 5, OS-AE is utilized as a generative model that can construct new data based on subspace features and perform better than conventional data augmentation techniques on real-world image and tabular datasets. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | Neural networks | en_US |
dc.subject | Network training algorithm | en_US |
dc.subject | Machine learning | en_US |
dc.subject | Online sequential learning | en_US |
dc.subject | Autoencoder | en_US |
dc.title | Online sequential learning with non-iterative strategy for feature extraction, classification and data augmentation | en_US |
dc.type | Thesis | en_US |
etd.degree.name | Master of Science | en_US |
etd.degree.level | Master | en_US |
etd.degree.discipline | Computer Science | en_US |
etd.degree.grantor | Lakehead University | en_US |
Appears in Collections: | Electronic Theses and Dissertations from 2009 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
PaulA2020m-1a.pdf | 5.15 MB | Adobe PDF | ![]() View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.