Feature Visualization: How neural nets build up their understanding of images
1–10 of 66 posts
Re: Feature Visualization: How neural nets build up their understanding of images
#2Hey! I'm one of the authors, along with Alex and Ludwig. We're happy to answer any questions! :)
Re: Feature Visualization: How neural nets build up their understanding of images
#3There’s also an appendix where you can browse all the layers. https://distill.pub/2017/feature-visualization/appendix/goog...
Re: Feature Visualization: How neural nets build up their understanding of images
#4Hey! I'm one of the authors, along with Alex and Ludwig. We're happy to answer any questions! :)
Many of the visualizations seem interpretable even though they are (essentially, I presume) projections of a very high dimensional space onto 2d position + 3d color space. Is there any research on projecting these visualizations into 6-dimensions as well (3d position + 3d color in VR) or even higher dimensions by substituting other sensory modalities for extra spacial or color dimensions?
Re: Feature Visualization: How neural nets build up their understanding of images
#5Awesome, 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...
Re: Feature Visualization: How neural nets build up their understanding of images
#6Hey! I'm one of the authors, along with Alex and Ludwig. We're happy to answer any questions! :)
Many of the visualizations seem interpretable even though they are (essentially, I presume) projections of a very high dimensional space onto 2d position + 3d color space. Is there any research on projecting these visualizations into 6-dimensions as well (3d position + 3d color in VR) or even higher dimensions by substituting other sensory modalities for extra spacial or color dimensions?
I suspect the extra fidelity won't have much payoff for high dimensions considering the large cognitive overhead required for a person to make sense of it. Even a six dimensional approximation of a 1,000 dimensional space is quite crude, and we're pretty confused by spaces larger than three.
Re: Feature Visualization: How neural nets build up their understanding of images
#7Hi Chris, firstly thanks for all the work you've done publishing brilliant articles on supervised and unsupervised methods and visualisation on your old blog and now in Distill.
This question isn't about feature visualisation, but I though I'd take the chance to ask you, what do you think of Hinton's latest paper and his move away from neural network architectures?
Re: Feature Visualization: How neural nets build up their understanding of images
#8Hi Chris, firstly thanks for all the work you've done publishing brilliant articles on supervised and unsupervised methods and visualisation on your old blog and now in Distill. This question isn't about feature visualisation, but I though I'd take the chance to ask you, what do you think of Hinton's latest paper and his move away from neural network architectures?
Capsules are cool! I spent several days hanging out with Geoff & co a few months back -- they're exploring really exciting directions. I don't feel like I have anything particularly exciting to add, though.
Re: Feature Visualization: How neural nets build up their understanding of images
#9Hi Chris, firstly thanks for all the work you've done publishing brilliant articles on supervised and unsupervised methods and visualisation on your old blog and now in Distill. This question isn't about feature visualisation, but I though I'd take the chance to ask you, what do you think of Hinton's latest paper and his move away from neural network architectures?
Capsules are cool! I spent several days hanging out with Geoff & co a few months back -- they're exploring really exciting directions. I don't feel like I have anything particularly exciting to add, though.
Thanks :D
Re: Feature Visualization: How neural nets build up their understanding of images
#10Awesome, 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...