Wasserstein GAN-Based Small-Sample Augmentation for New-Generation Artificial Intelligence: A Case Study of Cancer-Staging Data in Biology
It is essential to utilize deep-learning algorithms based on big data for the implementation of the new generation of artificial intelligence. Effective utilization of deep learning relies considerably on the number of labeled samples, which restricts the application of deep learning in an environme...
Main Authors: | Yufei Liu, Yuan Zhou, Xin Liu, Fang Dong, Chang Wang, Zihong Wang |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2019-02-01
|
Series: | Engineering |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2095809918301127 |
Similar Items
-
Generating Adversarial Samples With Constrained Wasserstein Distance
by: Kedi Wang, et al.
Published: (2019-01-01) -
WRGAN: Improvement of RelGAN with Wasserstein Loss for Text Generation
by: Ziyun Jiao, et al.
Published: (2021-01-01) -
An augmented Lagrangian approach to Wasserstein gradient flows and applications
by: Benamou Jean-David, et al.
Published: (2016-06-01) -
Physics-driven learning of Wasserstein GAN for density reconstruction in dynamic tomography
by: Huang, Z., et al.
Published: (2022) -
Physics-driven learning of Wasserstein GAN for density reconstruction in dynamic tomography
by: Huang, Z., et al.
Published: (2022)