# Generative Models For Deep Learning with Very Scarce Data

## TL;DR

This paper explores using Restricted Boltzmann Machines and Variational Auto-encoders to generate additional training data in scarce data scenarios, improving deep learning classification performance.

## Contribution

It compares RBMs and VAEs for data augmentation in deep learning, demonstrating RBMs' superior sample generation for better classifier generalization.

## Key findings

- RBMs outperform VAEs in sample quality for training
- Data augmentation improves classification accuracy in scarce data scenarios
- RBM-based augmentation surpasses semi-supervised ladder networks

## Abstract

The goal of this paper is to deal with a data scarcity scenario where deep learning techniques use to fail. We compare the use of two well established techniques, Restricted Boltzmann Machines and Variational Auto-encoders, as generative models in order to increase the training set in a classification framework. Essentially, we rely on Markov Chain Monte Carlo (MCMC) algorithms for generating new samples. We show that generalization can be improved comparing this methodology to other state-of-the-art techniques, e.g. semi-supervised learning with ladder networks. Furthermore, we show that RBM is better than VAE generating new samples for training a classifier with good generalization capabilities.