Development of learning algorithms for fully connect layers of convolutional neural network
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 con...
Main Author: | Wang, Yiming |
---|---|
Other Authors: | CHEAH Chien Chern |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/143189 |
Similar Items
-
Masked face recognition using convolutional neural network
by: Wu, Peihang
Published: (2023) -
Graph convolutional neural networks for text categorization
by: Lakhotia, Suyash
Published: (2018) -
Graph convolutional neural networks for the travelling salesman problem
by: Joshi, Chaitanya Krishna
Published: (2019) -
Facial expression recognition study based on convolutional neural network
by: Yu, Zhen Lin
Published: (2019) -
Gated convolutional neural network for fine-grained automatic essay scoring
by: Lee, Xing Zhao
Published: (2017)