Title

Comparative analysis of activation functions in neural networks

Document Type

Conference Proceeding

Publication Date

12-1-2021

Abstract

Although the impact of activations on the accuracy of neural networks has been covered in the literature, there is little discussion about the relationship between the activations and the geometry of neural network model. In this paper, we examine the effects of various activation functions on the geometry of the model within the feature space. In particular, we investigate the relationship between the activations in the hidden and output layers, the geometry of the trained neural network model, and the model performance. We present visualizations of the trained neural network models to help researchers better understand and intuit the effects of activation functions on the models.

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Volume

00

Disciplines

Computer Sciences

Keywords

Geometry, Analytical models, Shape, Neural networks, Fitting, Data visualization, Data models

Indexed in Scopus

no

Open Access

no

Share

COinS