Please use this identifier to cite or link to this item:
Title: Development of learning algorithms for fully connect layers of convolutional neural network
Authors: Wang, Yiming
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
Issue Date: 2020
Publisher: Nanyang Technological University
Abstract: In the field of transfer learning, pre-trained weights are usually used in the Convolutional Layers to get the features of the data and Fully Connected Layers are trained again for another classification task based on new training data. Inspired by the ideas of transfer learning and kinematic control algorithm in the field of robotics, this dissertation proposes a new learning algorithm which can be used to train the Fully Connected Layers in a simple way. It is observed based on the testing results of Cifar-10 that the algorithm is able to achieve a better accuracy at the start of the training while the accuracy of baseline method, Stochastic Gradient Descent, is lower at the beginning. The accuracy of the algorithm improves and becomes stable in the progress of learning. Thus, the algorithm has the potential of achieving a better performance in lesser epochs of training as compared with traditional Gradient Descent Method.
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
Development of learning algorithms for fully connect layers of convlutional neural network.pdf
  Restricted Access
876.21 kBAdobe PDFView/Open

Page view(s)

Updated on Jan 31, 2023


Updated on Jan 31, 2023

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.