LSTM classifiers require larger noise statistic separations than model-based EM classifiers to achieve reliable binary time series classification and saturate below the optimal Kalman filter reference when models differ only in measurement noise.
On the size of conv olutional neural networks and generalization performance,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Objective Performance Evaluation of the LSTM Networks in Time Series Classification
LSTM classifiers require larger noise statistic separations than model-based EM classifiers to achieve reliable binary time series classification and saturate below the optimal Kalman filter reference when models differ only in measurement noise.