Differential Equation Units: Learning Functional Forms of Activation Functions from Data
2020 ◽
Vol 34
(04)
◽
pp. 6030-6037
Keyword(s):
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation function from a family of solutions to an ordinary differential equation. Specifically, each neuron may change its functional form during training based on the behavior of the other parts of the network. We show that using neurons with DEU activation functions results in a more compact network capable of achieving comparable, if not superior, performance when compared to much larger networks.
2019 ◽
Vol 12
(3)
◽
pp. 156-161
◽
Overview of Configuring Adaptive Activation Functions for Deep Neural Networks - A Comparative Study
2021 ◽
Vol 3
(1)
◽
pp. 10-22
2021 ◽
Vol 15
(4)
◽
pp. 0-0
2021 ◽
2010 ◽
Vol 2010
◽
pp. 1-20
◽
Keyword(s):
2021 ◽
Vol 15
(4)
◽
pp. 1-15