Deep Neural Nets with Interpolating Function as Output Activation
Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley Osher
Abstract
We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function. And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function as output activation combines advantages of both deep and manifold learning. The new framework demonstrates the following major advantages: First, it is better applicable to the case with insufficient training data. Second, it significantly improves the generalization accuracy on a wide variety of networks. The algorithm is implemented in PyTorch, and the code is available at https://github.com/ BaoWangMath/DNN-DataDependentActivation.
BibTeX
@inproceedings{NEURIPS2018_6ecbdd6e,
author = {Wang, Bao and Luo, Xiyang and Li, Zhen and Zhu, Wei and Shi, Zuoqiang and Osher, Stanley},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Deep Neural Nets with Interpolating Function as Output Activation},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/6ecbdd6ec859d284dc13885a37ce8d81-Paper.pdf},
volume = {31},
year = {2018}
}