Are capsules a good idea? A generative perspective
I’ve recently written a paper on a fully probabilistic version of capsule networks. While trying to get this kind of model to work, I found some interesting conceptual issues with the ideas underlying capsule networks. Some of these issues are a bit philosophical in nature and I haven’t thought of a good way to pin them down in an ML conference paper. But I think they could inform research when we design new probabilistic vision models (and they are very interesting), so I’ve tried to give some insight into them here. This blog post is a companion piece to my paper: I start by introducing capsules from a generative probabilistic interpretation in a high level way, and then dive into a discussion about the conceptual issues I found. I will present the paper at the Object Oriented Learning workshop at ICML on Friday (July 17), so do drop by if you want to chat...
Are capsules a good idea? A generative perspective - OATML Lewis Smith , 10 Jul 2020 --> I’ve recently written a paper on a fully probabilistic version of capsule networks. While trying to get this kind of model to work, I found some interesting conceptual issues with the ideas underlying capsule networks. Some of these issues are a bit philosophical in nature and I haven’t thought of a good way to pin them down in an ML conference paper. But I think they could inform research when we design new probabilistic vision models (and they are very interesting), so I’ve tried to give some insight int
Explore this link on the map →related reading
- Capsule neural network - Wikipediaen.wikipedia.org
- Encapsulating Capsule Networks: Everything You Need To Know | Brennan Gebotysgebob19.github.io
- Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
- Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
- Generative modelling in latent space – Sander Dielemansander.ai
- Using Artificial Intelligence to Augment Human Intelligencedistill.pub
- Feature-wise transformationsdistill.pub
- The Platonic Representation Hypothesisphillipi.github.io
- The World Inside Neural Networksgoodfire.ai
- When Models Manipulate Manifolds: The Geometry of a Counting Tasktransformer-circuits.pub
- To Understand Language is to Understand Generalization | Eric Jangevjang.com
- Energy-Based Modelsenergy-based-model.github.io