Portal de Periódicos da CAPES

Learning Activation Functions to Improve Deep Neural Networks

2014; Cornell University; Linguagem: Inglês

Forest Agostinelli, Matthew D. Hoffman, Peter Sadowski, Pierre Baldi,

Medical Imaging Techniques and Applications

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.