Trent University Graduate Thesis Collection

Item Description
Identifier
tula:etd
Type
Collection
Language
eng
Extent
1 item
Rights
Copyright for all items in the Trent University Graduate Thesis Collection is held by the author, with all rights reserved, unless otherwise noted.
Displaying 1 - 2 of 2

Results per page

Displaying 1 - 2 of 2

SPAF-network with Saturating Pretraining Neurons

22852-Thumbnail Image.png
Year: 2016, 2016
Member of: Trent University Graduate Thesis Collection
Name(s): Creator (cre): Burhani, Hasham, Thesis advisor (ths): Wenying, Feng, Degree committee member (dgc): Hurley, Richard, Degree committee member (dgc): Abdella, Kenzu, Degree granting institution (dgg): Trent University
Abstract: <p>In this work, various aspects of neural networks, pre-trained with denoising autoencoders (DAE) are explored. To saturate neurons more quickly for feature learning in DAE, an activation function that offers higher gradients is introduced. Moreover, the introduction of sparsity functions applied to the hidden layer representations is studied. More importantly, a technique that swaps the… more
Full Text: SPAF-network with Saturating Pretraining Neurons A Thesis Submitted to the Committee of Graduate Studies in Partial Fulfillment of the Requirements for the Degree of Master of Science in the Faculty of Arts and Science TRENT UNIVERSITY Peterborough, …

Utilizing Class-Specific Thresholds Discovered by Outlier Detection

22241-Thumbnail Image.png
Year: 2016, 2016
Member of: Trent University Graduate Thesis Collection
Name(s): Creator (cre): Branch, Richard Arthur Conan, Thesis advisor (ths): McConnell, Sabine, Thesis advisor (ths): Hurley, Richard, Degree granting institution (dgg): Trent University
Abstract: <p>We investigated if the performance of selected supervised machine-learning techniques could be improved by combining univariate outlier-detection techniques and machine-learning methods. We developed a framework to discover class-specific thresholds in class probability estimates using univariate outlier detection and proposed two novel techniques to utilize these class-specific… more
Full Text: UTILIZING CLASS-SPECIFIC THRESHOLDS DISCOVERED BY OUTLIER DETECTION A Thesis Submitted to the Committee on Graduate Studies in Partial Fulfillment of the Requirements for the Degree of Master of Science in the Faculty of Arts and Science TRENT UNIVERSITY …