LGNEMLMay 2, 2020

A survey on modern trainable activation functions

arXiv:2005.00817v4524 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental work that synthesizes and categorizes existing research on trainable activation functions for the machine learning community.

The paper presents a survey of trainable activation functions in neural networks, organizing existing models into a taxonomy and discussing their properties and limitations.

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 of 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 constraints the corresponding weight layers.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes