Exploring Kervolutional Neural Networks

TL;DR

This paper analyzes the kervolutional neural network (KNN), a novel CNN variant, focusing on hyperparameter effects, alternative operations, and theoretical insights to understand its advantages over traditional CNNs.

Contribution

It provides an in-depth analysis of KNN architecture, including hyperparameter impacts, new kervolution operations, and theoretical understanding, expanding on the original concept.

Findings

KNN achieves faster convergence than CNNs.

KNN attains higher accuracy in experiments.

Hyperparameters significantly influence KNN performance.

Abstract

A paper published in the CVPR 2019 conference outlines a new technique called 'kervolution' used in a new type of augmented convolutional neural network (CNN) called a 'kervolutional neural network' (KNN). The paper asserts that KNNs achieve faster convergence and higher accuracies than CNNs. This "mini paper" will further examine the findings in the original paper and perform a more in depth analysis of the KNN architecture. This will be done by analyzing the impact of hyper parameters (specifically the learning rate) on KNNs versus CNNs, experimenting with other types of kervolution operations not tested in the original paper, a more rigourous statistical analysis of accuracies and convergence times and additional theoretical analysis. The accompanying code is publicly available.