41–50 of 66 posts
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???
Earlier quoted context omitted.
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…
This pictures reminds me about what one's can see under psychedelics. All sensory input basically begins to break down to that kind of patterns, and thus reality dissolves into nothing. This is equally terrifying and liberating depends on look. The terrifying thought is that there's no-one behind this eyes and ears. The liberating thought is that if there's no-one there, then there's no-one to die.
This didn't include my favorite kind of visualization from Nguyen, et al., 2015: https://i.imgur.com/AERgy7I.png
[1] Not technically a neural network, but a CPPN. Which is something like a neural network with many different mathematical functions as activation functions. This allows things like a neuron with a sine wave activation that can repeat a pattern across the image.
While I agree that the practicality of these visualizations mean that you have to fight against this high-frequency "cheating", I can't help but shake the feeling that what these optimization visualizations are showing us is correct. This is what the neuron responds to, whether you like it or not. Put in another way, the problem doesn't seem to be with the visualization but with the network itself.
Has there been any research in making neural networks that are robust to adversarial examples?
This didn't include my favorite kind of visualization from Nguyen, et al., 2015: https://i.imgur.com/AERgy7I.png
I should have explained how these are made. They train another neural network[1] to produce an image that most maximizes each class. This acts as a prior that the image must have a very simple and regular structure. And so the results seem to be very simple and even abstract, instead of pixel vomit. [1] Not technically a neural network, but a CPPN. Which is something like a neural network with many different mathemat…
hazarding a guess with no knowledge of the subject, I wonder if that is because no other class in ImageNet can be defined by orange and black. The net simply doesn't need to learn anything more about orange and black, because on 100% of the samples it trained on, orange and black meant "school bus". Every time. So no need to learn any other features -- if you see orange and black, it MUST be a school bus, at least in the context of this data set.
I wonder if we introduced other "orange and black" classes to ImageNet, it would need to learn more features about the school bus in order to identify it.
Interesting that simple optimization ends up with high-frequency noise similar to adversarial attacks on neural nets. While I agree that the practicality of these visualizations mean that you have to fight against this high-frequency "cheating", I can't help but shake the feeling that what these optimization visualizations are showing us is correct . This is what the neuron responds to, whether you like it or not. Pu…
This pictures reminds me about what one's can see under psychedelics. All sensory input basically begins to break down to that kind of patterns, and thus reality dissolves into nothing. This is equally terrifying and liberating depends on look. The terrifying thought is that there's no-one behind this eyes and ears. The liberating thought is that if there's no-one there, then there's no-one to die.
Seems like it isn't that reality dissolves into nothing, it's just a few channels that get overly stimulated.
Earlier quoted context omitted.
I should have explained how these are made. They train another neural network[1] to produce an image that most maximizes each class. This acts as a prior that the image must have a very simple and regular structure. And so the results seem to be very simple and even abstract, instead of pixel vomit. [1] Not technically a neural network, but a CPPN. Which is something like a neural network with many different mathemat…
the school bus one really sticks out to me. it seems all the net cares about is seeing orange juxtaposed with black. No shapes, no vehicle features, just orange and black. hazarding a guess with no knowledge of the subject, I wonder if that is because no other class in ImageNet can be defined by orange and black. The net simply doesn't need to learn anything more about orange and black, because on 100% of the samples…
It doesn't necessarily mean that color is the only feature it uses to classify school buses. Just that that feature alone is enough.
Earlier quoted context omitted.
the school bus one really sticks out to me. it seems all the net cares about is seeing orange juxtaposed with black. No shapes, no vehicle features, just orange and black. hazarding a guess with no knowledge of the subject, I wonder if that is because no other class in ImageNet can be defined by orange and black. The net simply doesn't need to learn anything more about orange and black, because on 100% of the samples…
That's a good observation. But when I see that image I definitely think of a school bus. The color pattern is very distinctive (in the US anyway where all school buses are painted the same color and style.) So I can't say the NN is wrong. It doesn't necessarily mean that color is the only feature it uses to classify school buses. Just that that feature alone is enough.