Abstract
dc:description.abstractThis work explores a novel generative modeling approach inspired by variational autoencoders (VAEs). Traditional VAEs rely on a recognition model (encoder) that approximates the latent posterior with a single gaussian distribution for each input, limiting their flexibility in capturing complex data distributions. In contrast, we propose a modified recognition model that utilizes stochastic mixtures of gaussians, allowing for a more expressive latent representation. By leveraging stochastic neural networks within the VAE framework, we aim to achieve a tighter evidence lower bound (ELBO) on the log-likelihood of the data. Our approach is a preliminary investigation to enhance the latent space structure and improve generative performance by incorporating richer uncertainty modeling.
Degree
thesis:*- Name thesis:degree_name
- Computer Science (MS)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Computer Science, Department of
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Desai, Shounak
- Contributors dc:contributor
-
- Richard D. Lange
Subjects
dc:subject × 1Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.rit.edu/theses/12243