Investigations in neural network learning using geometrical approach
In this thesis several methods to control the geometrical expansion process are proposed and analyzed. Our approaches turn out to gain faster training speed with satisfactory accuracy. We discuss problems both with Boolean inputs and with real-valued inputs respectively.
Saved in:
Main Author: | Wang, Di |
---|---|
Other Authors: | Narendra Shivaji Chaudhari |
Format: | Theses and Dissertations |
Published: |
2008
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/2517 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Similar Items
-
Investigating vulnerability of watermarking neural network
by: Chua, Viroy Sheng Yang
Published: (2020) -
Learning capabilities of neural networks
by: Huang, Guangbin.
Published: (2008) -
Stock trading prediction using deep learning neural networks
by: Ong, Hao Cong
Published: (2021) -
Complementary learning fuzzy neural network
by: Tan, Tuan Zea
Published: (2010) -
Federated learning for graph neural networks
by: Yan, Yige
Published: (2023)