Learning Activation Functions in Deep (Spline) Neural Networks
We develop an efficient computational solution to train deep neural networks (DNN) with free-form activation functions. To make the problem well-posed, we augment the cost functional of the DNN by adding an appropriate shape regularization: the sum of the second-order total-variations of the trainab...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Open Journal of Signal Processing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9264754/ |