/CapsNet

CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art

MIT LicenseMIT

CapsNet

CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules"

Table of Contents

What's New

Webinar

Implementations By Dataset

Toxic Comment Challenge (Kaggle)

Abstract

We cover here the last and most interesting paper's abstract about Capsule Networks.

We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote. The new mechanism 1) designs routing via inverted dot-product attention; 2) imposes Layer Normalization as normalization; and 3) replaces sequential iterative routing with concurrent iterative routing. When compared to previously proposed routing algorithms, our method improves performance on benchmark datasets such as CIFAR-10 and CIFAR-100, and it performs at-par with a powerful CNN (ResNet-18) with 4x fewer parameters. On a different task of recognizing digits from overlayed digit images, the proposed capsule model performs favorably against CNNs given the same number of layers and neurons per layer. We believe that our work raises the possibility of applying capsule networks to complex real-world tasks. Our code is publicly available at: https://github.com/apple/ml-capsules-inverted-attention-routing An alternative implementation is available at: https://github.com/yaohungt/Capsules-Inverted-Attention-Routing/blob/master/README.md

Excerpt from CAPSULES WITH INVERTED DOT-PRODUCT ATTENTION ROUTING, Yao-Hung Hubert Tsai, , Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov, ICLR 2020 🆕

UP

Documentation

Papers

UP

Articles

UP

Tutorials

Presentations

Webinar 🆕

Discussion Groups

Official Implementations

The implementations has been considered to be official since the authors were directly involved in the papers as co-authors or they had some references.

Proof of Work

Other Resources

Implementations by Framework

Pytorch

Pytorch + CUDA

Jupyter Notebook

Torch

Tensorflow

Keras

UP

MXNet

CNTK

Lasagne

Chainer

Matlab

R

C++

C

JavaScript

Vulcan

Other

UP

Implementations By Dataset

MNIST

IMDB Reviews

Cifar 10

BanglaLekha-Isolated Dataset:

Traffic Sign Dataset (German):

Iceberg Classification Challenge (Kaggle)

Toxic Comment Challenge (Kaggle)

UP

Implementations by Task

Text Classification

Speech Recognition

Emotion Recognition

Named Entity Recognition (NER)

Natural Language Processing (NLP)

UP

Translations

Japanese

Turkish

UP