Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Feature Visualization: How neural nets build up their understanding of images

distill.pub

Post reply on HN
Print view View original

11–20 of 66 posts

Re: Feature Visualization: How neural nets build up their understanding of images

#11

Post by Florin_Andrei »

osullivj wrote: post #10
nnfy wrote: post #5

Awesome, but to me this stuff is also terrifying, and I can't quite place why. Something about dissecting intelligence, and the potential that our own minds process things similarly. Creepy how our reality is distilled into these uncanny valley type matrices. Also, I suspect it says something that these images look like what people report seeing on psychedelic trips...

I remember friends telling me back in 88 [1] about driving round London from one rave to another high on MDMA & LSD. Back then I thought driving on acid was insane. This sounds like driving while the car is on acid! Which is a terrifying thought... [1] https://en.wikipedia.org/wiki/Second_Summer_of_Love

No, the acid simply lets you see "how the sausage is made". You get temporary access to intermediate layers that should probably remain hidden (and for good reasons).

With AI it's trivial to get access to the inner workings of the intermediate layers.

Re: Feature Visualization: How neural nets build up their understanding of images

#12

Post by cs702 »

colah3 wrote: post #2

Hey! 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 "most important" neuron activations / interactions of another DNN?

Re: Feature Visualization: How neural nets build up their understanding of images

#15

Post by AElsinore77 »

aj_g wrote: post #14

Wow. That's incredible how psychedelic these images are. I'd be really curious to learn more about the link between these two seemingly distant subjects.

Check out this: https://www.ted.com/talks/anil_seth_how_your_brain_hallucina...

Neural nets are doing something that the mind does too - it takes visual input, then it "predicts" and "fills in the blanks" (aka hallucinates) so that you "see" what you expect to see. Its why you dont notice your blind spot.

Its also interesting to note that this process appears to change as we age: https://www.npr.org/2016/04/17/474569125/your-brain-on-lsd-l...

Re: Feature Visualization: How neural nets build up their understanding of images

#16

Post by muxator »

Looking 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

Re: Feature Visualization: How neural nets build up their understanding of images

#17

Post by chillingeffect »

Are the layer names the same ones referred to in this paper? https://arxiv.org/abs/1409.4842

And how can e.g. layer3a be generated from layer conv2d0? By convolving with a linear kernel? Or by the entire Inception Module including the linear and the non-linear operations?

Thank you. Outstanding work breaking it down.

Here's another paper people might enjoy. The author generates an example for "Saxophone," which includes a player... Which is fascinating, bc it implies that our usage of the word in real practice implies a player, even though the Saxophone is an instrument only. This highlights the difference between our denotative language and our experience of language! https://www.auduno.com/2015/07/29/visualizing-googlenet-clas...

Also, for those curious about the DepthConcat operation, it's described here: https://stats.stackexchange.com/questions/184823/how-does-th...

Edit: I'll be damned if there isn't something downright Jungian about these prototypes! There are snakes! Man-made objects! Shelter structures! Wheels! Animals! Sexy legs! The connection between snakes and guitar bodies is blowing my mind!

Re: Feature Visualization: How neural nets build up their understanding of images

#18

Post by spiderfarmer »

muxator wrote: post #16

Looking 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.

Re: Feature Visualization: How neural nets build up their understanding of images

#19

Post by chillingeffect »

Is 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???

Post reply on HN