Interval LSTM and Interval Neural ODE models, trained with a quantile-style loss around pre-trained point models, produce prediction intervals that reach near-target coverage on three system identification benchmarks.
Initial results in power system identification from injected probing signals using a subspace method,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Introducing Interval Neural Networks for Uncertainty-Aware System Identification
Interval LSTM and Interval Neural ODE models, trained with a quantile-style loss around pre-trained point models, produce prediction intervals that reach near-target coverage on three system identification benchmarks.