English

Learning Activation Functions to Improve Deep Neural Networks

Neural and Evolutionary Computing 2015-04-22 v3 Computer Vision and Pattern Recognition Machine Learning Machine Learning

Abstract

Artificial neural networks typically have a fixed, non-linear activation function at each neuron. We have designed a novel form of piecewise linear activation function that is learned independently for each neuron using gradient descent. With this adaptive activation function, we are able to improve upon deep neural network architectures composed of static rectified linear units, achieving state-of-the-art performance on CIFAR-10 (7.51%), CIFAR-100 (30.83%), and a benchmark from high-energy physics involving Higgs boson decay modes.

Keywords

Cite

@article{arxiv.1412.6830,
  title  = {Learning Activation Functions to Improve Deep Neural Networks},
  author = {Forest Agostinelli and Matthew Hoffman and Peter Sadowski and Pierre Baldi},
  journal= {arXiv preprint arXiv:1412.6830},
  year   = {2015}
}

Comments

Accepted as a workshop paper contribution at the International Conference on Learning Representations (ICLR) 2015

R2 v1 2026-06-22T07:40:00.814Z