I was expecting meows.
I'll admit I too was expecting cat-centric "speech" synthesis.
Generating faces of cats using Generative Adversarial Networks
11–20 of 61 posts
Re: Generating faces of cats using Generative Adversarial Networks
#12Change the title? Seems like I wasn't the only one expecting some sort of audio-related thing.
Yeah, I put on headphones for this. Seems like a cat generator.
Re: Generating faces of cats using Generative Adversarial Networks
#13Re: Generating faces of cats using Generative Adversarial Networks
#14Re: Generating faces of cats using Generative Adversarial Networks
#15With this kind of task, how do you verify that you didn't just overfit and start reproducing the input data?
Yeah, I would have at least ran some kind of similarity search on the output. Without that check it's impossible to know if this is actually doing anything.
Re: Generating faces of cats using Generative Adversarial Networks
#16Re: Generating faces of cats using Generative Adversarial Networks
#17This is maybe the most important question for mankind that has ever been asked, so let me ask it: Would it also be possible to use this method to generate new images of attractive, half-naked female humans on the basis of an existing database of such images?
Re: Generating faces of cats using Generative Adversarial Networks
#18Earlier quoted context omitted.
She's generating it from noise: https://github.com/AlexiaJM/Deep-learning-with-cats/blob/mas... Also, you could verify by writing unit tests with OpenCV to look for similar sources. Since it's all headshots, it will find matches for sure, but it would also find with human faces.
The neural network is starting from noise, but that's not the only input, it was trained on [0] and I think it's arguable that the NN is "reproducing" the images from its training dataset in some sense. [0] https://web.archive.org/web/20150703060412/http://137.189.35...
Yep, this is a current area of research for content generation.
I think most current approaches build some transform to a latent space and then compare generated images with their nearest neighbors in the training set. If they're identical then your network just learned to reproduce the dataset.
Re: Generating faces of cats using Generative Adversarial Networks
#19Earlier quoted context omitted.
She's generating it from noise: https://github.com/AlexiaJM/Deep-learning-with-cats/blob/mas... Also, you could verify by writing unit tests with OpenCV to look for similar sources. Since it's all headshots, it will find matches for sure, but it would also find with human faces.
The neural network is starting from noise, but that's not the only input, it was trained on [0] and I think it's arguable that the NN is "reproducing" the images from its training dataset in some sense. [0] https://web.archive.org/web/20150703060412/http://137.189.35...
I think it's a very interesting question, of how can we measure when a neural network is being creative? In fact, creativity is not obvious at all. It's sort of an ill-posed question if you think about it. How can you verify that a network is generating things that are not like what it was trained on, yet are... like what it was trained on?
Are neural networks* forever relegated to the role of copying and interpolation? Do the neural network weights form a kind of database?
* (I don't think this only applies to neural networks, but models in general)
There was one recent work trying to address this [1] but I'm not 100% convinced and I think a lot more work is warranted in this area. A difficulty is that it's not a purely technical problem, but also one of semantics and interpretation. It's one that the "automatic musical accompaniment" community and other digital arts communities have struggled with for decades, and it's not resolved.
How do you know when a machine is being creative? It's not far from the moving goalposts problem of general artificial intelligence. How do you know when a machine is being intelligent, if you can always explain it away by examining the black box?