A Study on Generative Adversarial Networks Exacerbating Social Data Bias

A Study on Generative Adversarial Networks Exacerbating Social Data Bias

abstract: Generative Adversarial Networks are designed, in theory, to replicate the distribution of the data they are trained on. With real-world limitations, such as finite network capacity and training set size, they inevitably suffer a yet unavoidable technical failure: mode collapse. GAN-generat...

Full description

Bibliographic Details
Other Authors: Jain, Niharika (Author)
Format: Dissertation
Language:English
Published: 2020
Subjects:
Artificial intelligence
Computer science
Ethics
bias
data augmentation
generative adversarial network
machine learning
society
Online Access:http://hdl.handle.net/2286/R.I.57433

Internet

http://hdl.handle.net/2286/R.I.57433

Similar Items