Differential Equation Units: Learning Functional Forms of Activation Functions from Data
This addresses the inefficiency of neural network design by enabling adaptive activation functions, though it appears incremental as it builds on existing activation function methods.
The paper tackles the problem of using fixed activation functions in deep neural networks by introducing differential equation units (DEUs) that allow neurons to learn nonlinear activation functions from data, resulting in more compact networks achieving comparable or superior performance to larger networks.
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 is compared to much larger networks.