Learning Compact Neural Networks Using Ordinary Differential Equations as Activation Functions
arXiv:1905.07685
Abstract
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.
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Searching for Activation Functions
- Self-Normalizing Neural Networks
- Learning Activation Functions to Improve Deep Neural Networks
- ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections