Enhancing Sequential Model Performance with Squared Sigmoid TanH (SST) Activation Under Data Constraints

arXiv:2402.09034v1 Announce Type: new
Abstract: Activation functions enable neural networks to learn complex representations by introducing non-linearities. While feedforward models commonly use rectified linear units, sequential models like recurrent neural networks, long short-term memory (LSTMs) and gated recurrent units (GRUs) still rely on Sigmoid and TanH activation functions. However, these classical activation functions often struggle to model sparse patterns when trained on small sequential datasets to effectively capture temporal dependencies. To address this limitation, we propose squared Sigmoid TanH (SST) …

abstract arxiv constraints cs.ai cs.lg data functions learn linear long short-term memory memory networks neural networks performance recurrent neural networks sigmoid type units