G-NeuroDAVIS: A Neural Network model for generalized embedding, data visualization and sample generation

TL;DR

G-NeuroDAVIS is a novel neural network model that effectively visualizes high-dimensional data, generates realistic samples, and outperforms existing methods like VAE in embedding quality and classification tasks.

Contribution

The paper introduces G-NeuroDAVIS, a new generative model capable of generalized embedding, high-quality visualization, and sample generation, outperforming existing models such as VAE.

Findings

Superior embedding quality compared to VAE

Enhanced classification performance

Realistic and diverse sample generation

Abstract

Visualizing high-dimensional datasets through a generalized embedding has been a challenge for a long time. Several methods have shown up for the same, but still, they have not been able to generate a generalized embedding, which not only can reveal the hidden patterns present in the data but also generate realistic high-dimensional samples from it. Motivated by this aspect, in this study, a novel generative model, called G-NeuroDAVIS, has been developed, which is capable of visualizing high-dimensional data through a generalized embedding, and thereby generating new samples. The model leverages advanced generative techniques to produce high-quality embedding that captures the underlying structure of the data more effectively than existing methods. G-NeuroDAVIS can be trained in both supervised and unsupervised settings. We rigorously evaluated our model through a series of experiments, demonstrating superior performance in classification tasks, which highlights the robustness of the learned representations. Furthermore, the conditional sample generation capability of the model has been described through qualitative assessments, revealing a marked improvement in generating realistic and diverse samples. G-NeuroDAVIS has outperformed the Variational Autoencoder (VAE) significantly in multiple key aspects, including embedding quality, classification performance, and sample generation capability. These results underscore the potential of our generative model to serve as a powerful tool in various applications requiring high-quality data generation and representation learning.