Cognitive Consistency Routing Algorithm of Capsule-network

TL;DR

This paper introduces a cognitively inspired routing algorithm for capsule networks, aiming to enhance their similarity to human brain processing, and demonstrates improved performance over baseline models.

Contribution

It proposes a novel routing algorithm based on psychological cognitive consistency theories to improve capsule network performance.

Findings

Improved routing efficiency compared to baseline

Enhanced model alignment with human visual processing

Demonstrated performance gains in experiments

Abstract

Artificial Neural Networks (ANNs) are computational models inspired by the central nervous system (especially the brain) of animals and are used to estimate or generate unknown approximation functions relied on large amounts of inputs. Capsule Neural Network (Sabour S, et al.[2017]) is a novel structure of Convolutional Neural Networks which simulates the visual processing system of human brain. In this paper, we introduce psychological theories which called Cognitive Consistency to optimize the routing algorithm of Capsnet to make it more close to the work pattern of human brain. It has been shown in the experiment that a progress had been made compared with the baseline.