# Path Capsule Networks

## TL;DR

PathCapsNet is a deep, multi-path extension of CapsNet that improves performance and reduces parameters through novel routing and regularization techniques.

## Contribution

It introduces PathCapsNet, a deep multi-path architecture with new routing and regularization methods, addressing CapsNet's limitations in depth and parameter efficiency.

## Key findings

- Achieves comparable or better results than CapsNet.
- Reduces parameter count significantly.
- Demonstrates effectiveness of multi-path and fan-in routing.

## Abstract

Capsule network (CapsNet) was introduced as an enhancement over convolutional neural networks, supplementing the latter's invariance properties with equivariance through pose estimation. CapsNet achieved a very decent performance with a shallow architecture and a significant reduction in parameters count. However, the width of the first layer in CapsNet is still contributing to a significant number of its parameters and the shallowness may be limiting the representational power of the capsules. To address these limitations, we introduce Path Capsule Network (PathCapsNet), a deep parallel multi-path version of CapsNet. We show that a judicious coordination of depth, max-pooling, regularization by DropCircuit and a new fan-in routing by agreement technique can achieve better or comparable results to CapsNet, while further reducing the parameter count significantly.