Parabola-Based Artificial Neural Network Activation FunctionsThe paper deals with the issues of constructing logical
functions using artificial neurons
Parabola As an Activation Function of Artificial Neural Networks to the construction of an s-shaped
function is suitable for tuning a neural network through reverse error propagation
Парабола как функция активации искусственных нейронных сетей-shaped
function suitable for tuning a neural network by reverse error propagation is determined
Многослойные искусственные нейронные сети с функцией активации типа s-парабола и их приложения with the activation
function of the type "s-parabola" is presented. The setting was carried out based on the method
Реализация сигмоидной функции активации с помощью концепции перестраиваемых вычислительных средImplementation of the
sigmoid activation
function using the reconfigurable computing environments
A Bit-Parallel Representation of Activation Functions for Fast Neural Networks can be applied to activation
functions of various forms, including logistical and
sigmoid rational
Use of a Sigmoid Function to Describe Second Peak in Magnetization LoopsUse of a
Sigmoid Function to Describe Second Peak in Magnetization Loops
New method of training two-layer sigmoid neural networks using regularizationNew method of training two-layer
sigmoid neural networks using regularization