On the Transformation of Latent Space in Autoencoders

01/24/2019
by   Jaehoon Cha, et al.
0

Noting the importance of the latent variables in inference and learning, we propose a novel framework for autoencoders based on the homeomorphic transformation of latent variables --- which could reduce the distance between vectors in the transformed space, while preserving the topological properties of the original space --- and investigate the effect of the transformation in both learning generative models and denoising corrupted data. The results of our experiments show that the proposed model can work as both a generative model and a denoising model with improved performance due to the transformation compared to conventional variational and denoising autoencoders.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset