Reproducing Matrix Capsule Networks with EM Routing

A Modular and Faithful TensorFlow 2 Implementation

Master Thesis (2025)
Author(s)

S.G.J. Waltmann (TU Delft - Mechanical Engineering)

Contributor(s)

M. Wisse – Mentor (TU Delft - Mechanical Engineering)

R. Sabzevari – Graduation committee member (TU Delft - Aerospace Engineering)

C.A. van Hoof – Graduation committee member (TU Delft - Mechanical Engineering)

Faculty
Mechanical Engineering
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
26-08-2025
Awarding Institution
Delft University of Technology
Programme
Mechanical Engineering, Vehicle Engineering, Cognitive Robotics
Faculty
Mechanical Engineering
Downloads counter
34
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Matrix Capsule Networks with EM Routing, introduced by Hinton et al. (2018a), offer a powerful way to model part-whole relationships and pose information in neural networks. However, their broader adoption has been limited, possibly due in part to the complexity of the model and inconsistencies between the original paper and its official implementation. In this thesis, we present a faithful and modular reimplementation of the Matrix Capsule Network in TensorFlow 2, addressing missing and unclear aspects of the original description. Our implementation achieves competitive results on the SmallNORB dataset and is designed to be accessible, adaptable, and well-documented. By clarifying key architectural details and providing open-source code, we aim to support further research and lower the barrier to working with capsule-based models.

Files

License info not available