Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 19, 2025Open Access

Bayesian Modeling and Estimation of Linear Time-Variant Systems using Neural Networks and Gaussian Processes

View Full Paper
Ask AI
Bookmark
Share

Authors

YSYaniv Shulman

Discussion

Loading...

Member takes

Overview

This approach models impulse response with Gaussian processes, showing improved data efficiency and uncertainty quantification.

Key Points

  • The developed framework robustly infers characteristics of LTI systems from limited observations in noisy environments.
  • Experiments demonstrate better data efficiency, with enhanced inference capabilities for LTV impulse responses.
  • The methodology introduces uncertainty quantification, making it suitable for dynamic and challenging system identification tasks.
  • Using Bayesian neural networks and Gaussian processes, the approach naturally accommodates variations in system responses.

Cite This Study

Yaniv Shulman (2025) studied this question.

synapsesocial.com/papers/68f4b10d3d9d770bbc697088https://doi.org/10.48550/arxiv.2507.12878
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Canonical Bayesian Linear System Identification2025
  2. 2Nonlinear continuous‐time system identification by linearization around a time‐varying setpoint2024 · 4 citations
  3. 3Bayesian Networks for Variational System Identification2024
  4. 4Linearization Turns Neural Operators into Function-Valued Gaussian Processes2024 · 2 citations
  5. 5Mitigating Ill-posedness in Parameter Estimation under Sparse measurement for Linear time-varying systems employing Virtual Sensor Responses2024 · 1 citations