Learning Compact Neural Networks Using Ordinary Differential Equations as Activation Functions

05/19/2019
by   Ali Torkamani, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/06/2019

Differential Equation Units: Learning Functional Forms of Activation Functions from Data

Most deep neural networks use simple, fixed activation functions, such a...
research
04/18/2023

Amplifying Sine Unit: An Oscillatory Activation Function for Deep Neural Networks to Recover Nonlinear Oscillations Efficiently

Many industrial and real life problems exhibit highly nonlinear periodic...
research
02/24/2017

Activation Ensembles for Deep Neural Networks

Many activation functions have been proposed in the past, but selecting ...
research
06/30/2022

Consensus Function from an L_p^q-norm Regularization Term for its Use as Adaptive Activation Functions in Neural Networks

The design of a neural network is usually carried out by defining the nu...
research
02/06/2020

Almost Sure Convergence of Dropout Algorithms for Neural Networks

We investigate the convergence and convergence rate of stochastic traini...
research
03/18/2019

On-line learning dynamics of ReLU neural networks using statistical physics techniques

We introduce exact macroscopic on-line learning dynamics of two-layer ne...
research
12/09/2015

Stochastic Interpretation of Quasi-periodic Event-based Systems

Many networks used in machine learning and as models of biological neura...

Please sign up or login with your details

Forgot password? Click here to reset