Single-Example Learning in a Mixture of GPDMs with Latent Geometries

TL;DR

This paper introduces GPDMM, a probabilistic mixture model of GPDMs that effectively learns and generates human motion data from a single example, especially useful in medical applications with limited data.

Contribution

It presents the GPDMM, a novel mixture-of-experts model combining multiple GPDMs with geometric features for improved single-example human motion learning.

Findings

GPDMM achieves high classification accuracy.

GPDMM demonstrates strong generative capabilities.

Outperforms LSTMs, VAEs, and transformers in benchmarks.

Abstract

We present the Gaussian process dynamical mixture model (GPDMM) and show its utility in single-example learning of human motion data. The Gaussian process dynamical model (GPDM) is a form of the Gaussian process latent variable model (GPLVM), but optimized with a hidden Markov model dynamical prior. The GPDMM combines multiple GPDMs in a probabilistic mixture-of-experts framework, utilizing embedded geometric features to allow for diverse sequences to be encoded in a single latent space, enabling the categorization and generation of each sequence class. GPDMs and our mixture model are particularly advantageous in addressing the challenges of modeling human movement in scenarios where data is limited and model interpretability is vital, such as in patient-specific medical applications like prosthesis control. We score the GPDMM on classification accuracy and generative ability in single-example learning, showcase model variations, and benchmark it against LSTMs, VAEs, and transformers.