Dynamic Routing Between Capsules · HackerPapers discussions

Dynamic Routing Between Capsules — mentioned by vikashrungta

Wed, 08 Feb 2023 16:19:46 GMT

I posted a list of papers on twitter, and will be posting a summary for each of them as well. here is the list https://twitter.com/vrungta/status/1623343807227105280 Unlocking the Secrets of AI: A Journey through the Foundational Papers by @vrungta (2023) 1. "Attention is All You Need" (2017) - https://arxiv.org/abs/1706.03762 (Google Brain) 2. "Generative Adversarial Networks" (2014) - https://arxiv.org/abs/1406.2661 (University of Montreal) 3. "Dynamic Routing Between Capsules" (2017) - https://arxiv.org/abs/1710.09829 (Google Brain) 4. "Unsupervised Representation Learning with Deep…

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by cs702

Sun, 03 May 2020 21:48:41 GMT

I'm surprised there is no mention of capsules and capsule-routing algorithms. Capsules are groups of neurons that represent discrete entities in different contexts. For example, a 4x4 pose matrix is a capsule representing a particular object in different orientations seen from different viewpoints. Similarly, a subword embedding can be seen as a capsule with vector shape representing a particular subword in different natural language contexts. More generally, a capsule can have any shape, but it always represents only one entity in some context. In certain new capsule-routing algorithms…

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by cs702

Fri, 19 Jul 2019 17:31:18 GMT

Keno: first of all, let me give a big public thank you to you and your colleagues. (For those here who don't know, Keno is listed as one of the authors of the paper, and works closely with Mike Innes, lead author and also lead developer of Zygote. Mike is also an active member of HN.) Second, let me bring up what I think is a significant issue. My perception is that most deep learning researchers and practitioners -- that includes me -- tend to iterate very rapidly over new ideas. We want to test ideas in code as quickly as possible, and in practice we will not invest the time and effort…

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by cs702

Fri, 28 Jun 2019 14:24:52 GMT

Direct link to the Google Brain paper, which is well worth a read: https://dl.acm.org/citation.cfm?id=3321441 (click on "PDF" link to read) Abstract: "In this paper we argue that systems for numerical computing are stuck in a local basin of performance and programmability. Systems researchers are doing an excellent job improving the performance of 5-year-old benchmarks, but gradually making it harder to explore innovative machine learning research ideas. We explain how the evolution of hardware accelerators favors compiler back ends that hyper-optimize large monolithic kernels, show how this…

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by dr_zoidberg

Mon, 11 Jun 2018 13:47:39 GMT

You made me think of the Margaret Thatcher Illusion, for which the best example I found was Dr. Phil Plait[0]. Funny thing, the idea of Capsule Networks (Hinton et al)[1, 2] seems to tackle some of these issues, though it's they're a bit young yet and more more work. [0] https://www.opticalspy.com/opticals/dr-phil-plait-optical-il... [1] https://arxiv.org/abs/1710.09829 [2] https://hackernoon.com/what-is-a-capsnet-or-capsule-network-...

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by xvedejas

Fri, 23 Feb 2018 22:35:27 GMT

I wonder how well capsule networks could deal with this, considering they're more robust than traditional CNNs towards other sorts of adversarial attacks. My guess is that one-pixel changes are going to do very little to alter pose information (though they will still alter the confidence of the feature existing), and so caps nets should be more robust here as well. Does anyone know if my intuition is correct? Link to the capsule network paper, for those who haven't heard of it: https://arxiv.org/abs/1710.09829

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by babak_ap

Sat, 13 Jan 2018 17:40:10 GMT

Is the mechanism of 'Arc' gene related to the dynamic routing process of Capsule networks [1, 2]? [1] https://kndrck.co/posts/capsule_networks_explained/ [2] https://arxiv.org/abs/1710.09829

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by leecarraher

Sat, 30 Dec 2017 22:20:29 GMT

Dynamic Routing Between Capsules the long awaited paper from Geoffrey Hinton (although Sara Sabour is principal author, Hinton has been hinting at this for a while now) on an alternative to back-propagation https://arxiv.org/abs/1710.09829

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by arketyp

Thu, 30 Nov 2017 12:27:24 GMT

I sympathize with this being in a similar professional situation and having once been introduced to this field via Hofstadter. His musings are usually on a distinctly symbolic level however, and though it is not my intention to defend a kind of results-only pragmatic approach, I do concern myself with strategies for progressively reaching better models of intelligence and their realization in contemporary hardware in particular. What, for instance, is your opinion about Hinton's recently published capsules idea? https://arxiv.org/abs/1710.09829 https://openreview.net/forum?id=HJWLfGWRb

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by Smerity

Mon, 27 Nov 2017 06:42:48 GMT

Capsule networks[1] have literally not been used on anything larger than what is considered a toy dataset for computer vision yet. Whilst there is potential there I'd argue it's too early to ascribe extreme levels of excitement towards it. [1]: https://arxiv.org/abs/1710.09829

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by skierscott

Fri, 17 Nov 2017 04:42:13 GMT

> 2% is HUGE at this point Hell, on MNIST 0.14% is huge. Geff Hinton created an entire new architecture to get 0.25% error, which is far better than the baseline 0.39% error [1]. To be fair, he did reduce the error by 35%. [1]:https://arxiv.org/pdf/1710.09829.pdf

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by stablemap

Fri, 10 Nov 2017 17:33:37 GMT

This doesn’t add much on top of the Wired article. Lots of comments on that: https://news.ycombinator.com/item?id=15609402 Here’s the paper: https://arxiv.org/abs/1710.09829

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by SophosQ

Fri, 03 Nov 2017 07:40:26 GMT

The only thing is that, when this presentation was given, it seems they hadn't worked much more than MNIST (so the new thing now would be the toys-recognition net). The paper however details their experiments on Cifar-10 and other datasets in the discussion section. They don't produce good enough results but the paper proposes certain hypotheses for the poorer performance and that it could be overcome in the future. Arxiv-link: https://arxiv.org/abs/1710.09829

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — HN submission

Thu, 02 Nov 2017 14:32:01 GMT

Dynamic Routing Between Capsules

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Dynamic Routing Between Capsules — mentioned by cbennett

Wed, 01 Nov 2017 20:10:42 GMT

To save you clicks, the two pre-prints are at : https://arxiv.org/pdf/1710.09829.pdf && https://openreview.net/pdf?id=HJWLfGWRb

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — HN submission

Wed, 01 Nov 2017 01:01:14 GMT

Dynamic Routing Between Capsules by Sabour, Frosst, Geoffrey E Hinton (CapsNet))

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Dynamic Routing Between Capsules — mentioned by grzm

Wed, 01 Nov 2017 00:51:35 GMT

The article discussed in the review is "Dynamic Routing Between Capsules": https://arxiv.org/abs/1710.09829

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — mentioned by nl

Tue, 31 Oct 2017 09:10:02 GMT

This is trueish, but there is more to it than that. It is true for sure that absolute performance on MNIST isn't the most interesting thing in the world. But when introducing a new tool or technique being able to show competitive performance on MNIST is a good way to show that it isn't an entirely useless thing. I'd note that recent Sabour, Frosst and Hinton paper[1] (where they finally got Hinton's capsules to work) spends most of the paper analyzing how it performs on MNIST, and only a short section on other datasets. I assume I don't need to point out that Geoff Hinton does know a little…

Paper and discussion history. A mention is not an endorsement.

Dynamic Routing Between Capsules — HN submission

Sun, 29 Oct 2017 01:08:21 GMT

Dynamic Routing Between Capsules

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Dynamic Routing Between Capsules — HN submission

Fri, 27 Oct 2017 16:29:46 GMT

Dynamic Routing Between Capsules

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Dynamic Routing Between Capsules — HN submission

Fri, 27 Oct 2017 04:44:10 GMT

Dynamic Routing Between Capsules [pdf]

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.