Generative modeling through internal high-dimensional chaotic activity

TL;DR

This paper investigates using internal high-dimensional chaotic dynamics as a novel method for generative modeling, demonstrating that simple learning rules can produce data with statistical properties similar to training datasets.

Contribution

It introduces a new approach to generative modeling leveraging chaotic systems' internal dynamics, bypassing the need for external noise.

Findings

Chaotic dynamics can be harnessed for data generation.

Simple learning rules are effective in training these systems.

Generated data matches statistical properties of training data.

Abstract

Generative modeling aims at producing new datapoints whose statistical properties resemble the ones in a training dataset. In recent years, there has been a burst of machine learning techniques and settings that can achieve this goal with remarkable performances. In most of these settings, one uses the training dataset in conjunction with noise, which is added as a source of statistical variability and is essential for the generative task. Here, we explore the idea of using internal chaotic dynamics in high-dimensional chaotic systems as a way to generate new datapoints from a training dataset. We show that simple learning rules can achieve this goal within a set of vanilla architectures and characterize the quality of the generated datapoints through standard accuracy measures.