SwishReLU: A Unified Approach to Activation Functions for Enhanced Deep Neural Networks Performanceby Jamshaid Ul…
Swish-T : Enhancing Swish Activation with Tanh Bias for Improved Neural Network Performanceby Youngmin Seo,…
Hadamard Representations: Augmenting Hyperbolic Tangents in RLby Jacob E. Kooi, Mark Hoogendoorn, Vincent François-LavetFirst submitted…
On Non-asymptotic Theory of Recurrent Neural Networks in Temporal Point Processesby Zhiheng Chen, Guanhua Fang,…
Hyperplane Arrangements and Fixed Points in Iterated PWL Neural Networksby Hans-Peter BeiseFirst submitted to arxiv…
Gradient Flow Based Phase-Field Modeling Using Separable Neural Networksby Revanth Mattey, Susanta GhoshFirst submitted to…
Enhancing Sequential Model Performance with Squared Sigmoid TanH (SST) Activation Under Data Constraintsby Barathi Subramanian,…
Task structure and nonlinearity jointly determine learned representational geometryby Matteo Alleman, Jack W Lindsey, Stefano…