@misc{10481/108771,
year = {2025},
month = {7},
url = {https://hdl.handle.net/10481/108771},
abstract = {The recognized learning ability of neural networks (NNs) is determined by their training process. The NN
data-dependent nature makes that their success depends to a large extent on the quality of the training data
sets. This paper addresses the selection of the best training sets for Long Short Time Models (LSTMs) in reallife contexts. If such selection from a theoretical standpoint is already complex, it becomes challenging when
addressed for real scenarios, where effectiveness should be replaced by efficiency (i.e., effectiveness in the
shortest possible time and without increasing the computational cost).
Our proposal revolves around the introduction, definition and structuring of a new LSTM gate: the efficiency
gate, that applies to those inputs that have passed the forget gate. The efficiency gate is responsible for ensuring
that training advances only with the best inputs in the sense that the corresponding outputs match as closely as
possible with a target value (best estimators). For this purpose, new mathematical results will be demonstrated
here in order to prove that our efficiency gate is mathematically feasible.
We also fully describe how the new gate joins the LSTM operation, blending in with it. The consequence
of such natural integration is that the computational effort is practically unchanged. Our methodology also
allows the user to set the admissible error thresholds (which are different in each real scenario) as part of the
setting options.},
organization = {MCIN/AEI - ERDF “A way of making Europe” (PID2022-139297OB-I00)},
organization = {Junta de Andalucía (P12.SEJ.2463; TIC186)},
organization = {MCIN/AEI - Unidad de Excelencia “María de Maeztu” (IMAG, CEX2020-001105-M)},
organization = {Universidad de Granada - CBUA (Open access funding)},
publisher = {Elsevier},
keywords = {Efficiency gate},
keywords = {New LSTM gate},
keywords = {Selection of training data sets},
title = {LSTM new gate for computing the efficiency on inputdata},
doi = {10.1016/j.knosys.2025.113622},
author = {García Cabello, Julia and Carbó-García, Santiago},
}