Feeding past prediction errors back into RNN, GRU, and LSTM hidden-state updates improves short-horizon forecasting accuracy on ETT benchmarks with only a 0.73% parameter increase.
Short-term residential load forecasting based on LSTM recurrent neural network,
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
-
IRNN: Innovation-driven Recurrent Neural Network for Time-Series Data Modeling and Prediction
Feeding past prediction errors back into RNN, GRU, and LSTM hidden-state updates improves short-horizon forecasting accuracy on ETT benchmarks with only a 0.73% parameter increase.