Activation Function Modulation in Generative Triangular Recurrent Neural Networks

Autonomous generation of time series is challenging because the network must capture short-term features while tracking long-term time dependencies. This paper introduces the modulation of the activation function slopes of the upper-lower triangular recurrent neural networks (ULTRNNs) for dynamic va...

Celý popis

Uloženo v:
Podrobná bibliografie
Hlavní autoři: Seshadri Sivakumar, Shyamala Sivakumar
Médium: Artigo
Jazyk:Inglês
Vydáno: IEEE 2022-01-01
Edice:IEEE Access
Témata:
Triangular RNN
activation function slope modulation
generative networks
closed-loop training
On-line přístup:https://ieeexplore.ieee.org/document/9762727/
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!

Podobné jednotky