Single-Example Learning in a Mixture of GPDMs with Latent Geometries
Single-Example Learning in a Mixture of GPDMs with Latent Geometries
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.
Jesse St. Amand、Leonardo Gizzi、Martin A. Giese
医学研究方法生物科学研究方法、生物科学研究技术计算技术、计算机技术
Jesse St. Amand,Leonardo Gizzi,Martin A. Giese.Single-Example Learning in a Mixture of GPDMs with Latent Geometries[EB/OL].(2025-06-17)[2025-07-18].https://arxiv.org/abs/2506.14563.点此复制
评论