Hey! I'm one of the authors, along with Alex and Ludwig. We're happy to answer any questions! :)
I wanted to thank you not only for this new page but also for your blog and distill.pub, especially the research debt page!
Feature Visualization: How neural nets build up their understanding of images
21–30 of 66 posts
Re: Feature Visualization: How neural nets build up their understanding of images
#22Looking at the finger instead of the moon: I like the HTML layout (responsive, inline images with captions, lateral notes). Any insights on how it's generated? Markdown, Rst, Latex -> HTML? I would love to produce my documentation in this way. Edit: I was too hurried. Everything is explained in https://distill.pub/guide/ , the template is at https://github.com/distillpub/template
I logged in to comment on the superb design as well. The design doesn’t only make it look good, every aspect is in full support of the content. And technically it’s executed perfectly as well. Very impressive.
I'm incredibly lucky to be working with a number of people who have an amazing intersection of design skills and scientific knowledge.
Ludwig is fantastic and put an incredible amount of work into polishing this article. And my co-editor Shan (who used to do data vis at the New York Times) seems like he has super powers half the time. We also get lots of outstanding advice from Ian Johnson and Arvind Satyanarayan.
Re: Feature Visualization: How neural nets build up their understanding of images
#23Hey! I'm one of the authors, along with Alex and Ludwig. We're happy to answer any questions! :)
As always, THANK YOU. You and your coauthors' attention to even the smallest details everywhere in this piece are evident. I've added it to my reading list, to read through it and look at the visualizations slowly :-) That said, after skimming the piece and thinking about the amount of work that went into it, one question popped up in my mind: do you think it would be possible to train a DNN to learn to visualize the…
We're glad you enjoyed it! :D
> do you think it would be possible to train a DNN to learn to visualize the "most important" neuron activations / interactions of another DNN?
That sounds like a really hard problem. I'm not entirely sure what it would mean even, but it would not surprise me at all if there was some refinement that could turn into an interesting research direction! :)
Re: Feature Visualization: How neural nets build up their understanding of images
#24Earlier quoted context omitted.
As always, THANK YOU. You and your coauthors' attention to even the smallest details everywhere in this piece are evident. I've added it to my reading list, to read through it and look at the visualizations slowly :-) That said, after skimming the piece and thinking about the amount of work that went into it, one question popped up in my mind: do you think it would be possible to train a DNN to learn to visualize the…
We're glad you enjoyed it! :D > do you think it would be possible to train a DNN to learn to visualize the "most important" neuron activations / interactions of another DNN? That sounds like a really hard problem. I'm not entirely sure what it would mean even, but it would not surprise me at all if there was some refinement that could turn into an interesting research direction! :)
Thanks. I asked the question in such an open-ended way just to see if you had any crazy ideas. It does sound like a hard problem.
In terms of what it could mean, one idea I just had is to take a trained model, randomly remove (e.g., zero out) neurons, and then train a second model to predict how well the trained model continues to work without those removed neurons. The goal would not be to 'thin out' the first model to reduce computation, but to train the second one learn to identify important neurons/interactions. Perhaps the second model can learn to predict which neurons/interactions are most important to the first model, as a stepping stone for further analysis?
Re: Feature Visualization: How neural nets build up their understanding of images
#25Re: Feature Visualization: How neural nets build up their understanding of images
#26Earlier quoted context omitted.
I logged in to comment on the superb design as well. The design doesn’t only make it look good, every aspect is in full support of the content. And technically it’s executed perfectly as well. Very impressive.
I'm incredibly lucky to be working with a number of people who have an amazing intersection of design skills and scientific knowledge. Ludwig is fantastic and put an incredible amount of work into polishing this article. And my co-editor Shan (who used to do data vis at the New York Times) seems like he has super powers half the time. We also get lots of outstanding advice from Ian Johnson and Arvind Satyanarayan.
Minor note, you should add the field DOI={10.23915/distill.00007} to the BibTeX citation. This is also missing from Google scholar, and is a particular pat peeve of mine now that DOIs are practically mandatory (copying the helpfully-formatted citation but then having to look around the page to find the DOI).
Re: Feature Visualization: How neural nets build up their understanding of images
#27Is there any way to run images from a camera real-time into GoogLeNet? E.g. like if I want to scan areas around me to see if there are any perspectives in my environment that light up the "snake" neurons or the dog neurons???
You might find it interesting to look at Jason Yosinski's "deep vis" framework: http://yosinski.com/deepvis
Re: Feature Visualization: How neural nets build up their understanding of images
#28Earlier quoted context omitted.
I'm incredibly lucky to be working with a number of people who have an amazing intersection of design skills and scientific knowledge. Ludwig is fantastic and put an incredible amount of work into polishing this article. And my co-editor Shan (who used to do data vis at the New York Times) seems like he has super powers half the time. We also get lots of outstanding advice from Ian Johnson and Arvind Satyanarayan.
Minor note, you should add the field DOI={10.23915/distill.00007} to the BibTeX citation. This is also missing from Google scholar, and is a particular pat peeve of mine now that DOIs are practically mandatory (copying the helpfully-formatted citation but then having to look around the page to find the DOI).
Thanks for the suggestion, added it to our issues... https://github.com/distillpub/template/issues/62
Re: Feature Visualization: How neural nets build up their understanding of images
#29Earlier quoted context omitted.
I'm incredibly lucky to be working with a number of people who have an amazing intersection of design skills and scientific knowledge. Ludwig is fantastic and put an incredible amount of work into polishing this article. And my co-editor Shan (who used to do data vis at the New York Times) seems like he has super powers half the time. We also get lots of outstanding advice from Ian Johnson and Arvind Satyanarayan.
Minor note, you should add the field DOI={10.23915/distill.00007} to the BibTeX citation. This is also missing from Google scholar, and is a particular pat peeve of mine now that DOIs are practically mandatory (copying the helpfully-formatted citation but then having to look around the page to find the DOI).
Thanks for the heads-up! We are not sure there is a standard for this, but we now include the DOI in our bibtex citation.
Re: Feature Visualization: How neural nets build up their understanding of images
#30Cool. Reminds me a bit of https://qualiacomputing.com/2016/12/12/the-hyperbolic-geomet...
(Though maybe not as symmetric?)