A survey on modern trainable activation functions

By Andrea Apicella, Francesco Donnarumma, Francesco Isgrò, Roberto Prevete. Neural Networks, 2020

533 citations recorded by the source corpus.

In neural networks literature, there is a strong interest in identifying and defining activation functions which can improve neural network performance. In recent years there has been a renovated interest in the scientific community in investigating activation functions which can be trained during the learning process, usually referred to as trainable, learnable or adaptable activation functions. They appear to lead to better network performance. Diverse and heterogeneous models of trainable activation function have been proposed in the literature. In this paper, we present a survey of these models. Starting from a discussion on the use of the term "activation function" in literature, we propose a taxonomy of trainable activation functions, highlight common and distinctive proprieties of recent and past models, and discuss main advantages and limitations of this type of approach. We show that many of the proposed approaches are equivalent to adding neuron layers which use fixed (non-trainable) activation functions and some simple local rule that constrains the corresponding weight layers.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/9f5d7836932bbb7a033f824c50c8ea28e8495daf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Bidyut Baran Chaudhuri
  2. Satish Kumar Singh
  3. Shiv Ram Dubey

Citations in the corpus