Identifiable Representation and Model Learning for Latent Dynamic Systems
Learning identifiable representations and models from low-level observations is helpful for an intelligent spacecraft to complete downstream tasks reliably. For temporal observations, to ensure that the data generating process is provably inverted, most existing works either assume that the noise va...
Saved in:
Main Authors: | Congxi Zhang, Yongchun Xie |
---|---|
Format: | Article |
Language: | English |
Published: |
American Association for the Advancement of Science (AAAS)
2025-01-01
|
Series: | Space: Science & Technology |
Online Access: | https://spj.science.org/doi/10.34133/space.0267 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Multimodal Latent Representation Learning for Video Moment Retrieval
by: Jinkwon Hwang, et al.
Published: (2025-07-01) -
LatentPINNs: Generative physics-informed neural networks via a latent representation learning
by: Mohammad H. Taufik, et al.
Published: (2025-06-01) -
Multi-step prediction in linearized latent state spaces for representation learning
by: Андрій Титаренко
Published: (2022-10-01) -
Dual-Stream Contrastive Learning for Medical Visual Representations Using Synthetic Images Generated by Latent Diffusion Model
by: Weitao Ye, et al.
Published: (2025-01-01) -
Determination of the latent geometry of atorvastatin pharmacokinetics by transfer entropy to identify bottlenecks
by: Paola Lecca, et al.
Published: (2025-06-01)