Presenter(s)

    Fangshi Zhou

    Comments

    Presentation: 11:20-11:40 p.m., Jessie Hathcock Hall 180

    Download

    Download Project (1.2 MB)

    Description

    Recently variational autoencoders (VAE) have become one of the most popular generative models in deep learning. It can be applied to generate images, audio, text, and other data. We propose a novel parallel structure for Gumbel-Softmax VAEs, which combines m ≥ 1 parallel VAEs with different annealing mechanics for softmax temperature τ and adjusts τ at each training epoch based on the minimum loss from these VAEs. Our preliminary experiments demonstrate that our model with m > 1 (e.g., m = 5) outperforms the model with m = 1 in generative processes, adversarial robustness, and denoising.

    Publication Date

    4-19-2023

    Project Designation

    Graduate Research

    Primary Advisor

    Zhongmei Yao, Xin Chen, Luan Nguyen, Tianming Zhao

    Primary Advisor's Department

    Computer Science

    Keywords

    Stander Symposium, College of Arts and Sciences

    Institutional Learning Goals

    Vocation

    MinLoss-VAE: Min-Loss Parallel Variational Autoencoders with Categorical Latent Space

    Share

    COinS