Year: 2016, 2016
Member of: Trent University Graduate Thesis Collection
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, …