Introduces squared sigmoid-tanh (SST) activation for GRU gates and reports consistent outperformance versus standard GRUs, largest in smallest-data regimes across sign language, activity recognition, and time-series tasks.
Overcoming the vanish- ing gradient problem during learning recurrent neural nets (rnn).Asian Journal of Applied Science and Engineering, 9:197–208,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning
Introduces squared sigmoid-tanh (SST) activation for GRU gates and reports consistent outperformance versus standard GRUs, largest in smallest-data regimes across sign language, activity recognition, and time-series tasks.