Escaping from Collapsing Modes in a Constrained Space
碩士 === 國立清華大學 === 資訊工程學系所 === 106 === Generative adversarial networks (GANs) often suffer from unpredictable mode- collapsing during training. We study the issue of mode collapse of Boundary Equilib- rium Generative Adversarial Network (BEGAN), which is one of the state-of-the-art generative models....
Main Authors: | Chang, Chia-Che, 張嘉哲 |
---|---|
Other Authors: | Lee, Che-Rung |
Format: | Others |
Language: | en_US |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/kjdve5 |
Similar Items
-
Escaping saddle points in constrained optimization
by: Mokhtari, Aryan, et al.
Published: (2019) -
Length-constrained Escape Routing of Differential Pairs
by: Yi-Hsun Hsiao, et al.
Published: (2014) -
Spherical Collapse Models with Clustered Dark Energy
by: Chang, Chia-Chun, et al.
Published: (2018) -
Efficient Direction-Constrained Layer Assignment for Rectangle Escape Routing
by: Yu, Ming-Chun, et al.
Published: (2014) -
A Novel Full-Mode Shift Network Design in Layered LDPC Decoder for IEEE 802.11n Applications
by: Che-ChiaChang, et al.
Published: (2013)