lucidrains

Thanks for all the upvotes! Since I made this site, people have already started to train on datasets beyond just real faces. Turns out it can disentangle pretty much any set of data.

Gwern has applied this to anime dataset https://twitter.com/gwern/status/1095131651246575616

Cyril at Google has applied it to artwork https://twitter.com/kikko_fr/status/1094685986691399681

This was to raise awareness for what a talented group of researchers made at Nvidia over the course of 2 years, the latest state of the art for GANs. https://arxiv.org/pdf/1812.04948.pdf (https://github.com/NVlabs/stylegan)

Rani Horev wrote up a nice description of the architecture here. https://www.lyrn.ai/2018/12/26/a-style-based-generator-archi...

Feel free to experiment with the generations yourself at a colab I made https://colab.research.google.com/drive/1IC0g2oDQenrDmwbtkKo...

I'm currently working on a project to map BERT embeddings of text descriptions of the faces directly to the latent space embedding (which is just a 512 dimensional vector). The goal is to control the image generation with sentences, once the mapping network is trained. Will definitely post on hacker news again if that succeeds. The future is now!

This is just to raise awareness for how powerful the generative models have become with the recently open sourced https://github.com/NVlabs/stylegan

Based on work from https://arxiv.org/abs/1812.04948

From the researcher mentioned in the article https://github.com/aqlaboratory/proteinnet

Great job with the app! Which open source model did you use to generate the speech?

I'm sure that once the dust settles, we will have an AlphaZero version for AlphaStar as well

Second this! Thank you for the wonderful explanation

Which makes the compelling results of deep networks even more mysterious. (https://gandissect.csail.mit.edu/) How could we have captured the seemingly enormously complex act of visual object recognition, with all the neurons and synapses and chemicals, in something so crude and simple as backpropagation and stochastic gradient descent with a bunch of ones and zeros? Or perhaps both processes, biological and artificial, point to a more fundamental emergent phenomenon of the computational universe we inhabit?

the BERT language model https://ai.googleblog.com/2018/11/open-sourcing-bert-state-o...

No. There is going to be an Alphago moment for every industry.

what's your email??

Ok! Was originally going to reach out to Sebastian Ruder and see if nlpprogress.com could be automated

I was just about to build this! Arghh you beat me to it..

Thank you for this!

Yea, you are right. That's the current thought.

I think Numenta is basing their claim on other studies that suggest there are grid cell like signatures in the neocortex, thus leading to the rampant speculation.

I think you misunderstood the paper. Grid cells don't encode location, a set of grid cell modules do. So there isn't a grandmother cell here at all. He's simply proposing this theory because of the noted presence of grid cells in the neocortex.

His new theory, if I understand it correctly, is pretty basic. It is simply saying every sparse encoding of sensory inputs is also tied to a spatial encoding by sets of grid cell modules within the same cortical column. For deep learning practitioners, it would be like saying every embedding comes with it's own spatial encoding, or placed into the same embedding space, however you want to look at it.

These spatial encodings are then related to other spatial encodings of other sensory inputs on different cortical column stacks (by displacement cells?), to firstly build up representations of objects, and then, he surmises further, the relationships of these objects with each other (part to whole).

I think the last part is probably what Jeff will need to substantiate a bit more.

Numenta also put out a video recently explaining this new theory https://www.youtube.com/watch?v=LNRZD9YJCdI

you're welcome! :)

one of the best visual tutorials on the transformer I came across http://jalammar.github.io/illustrated-transformer/

tensorflow hub? https://www.tensorflow.org/hub/

Nice! I just tried transcribing myself playing Waltz For Debby and it worked well! Too bad I couldn't find a place to share the resulting midi.

Never mentioned AI. Simply noting that the mathematical tool used here is inspired by the brain.

When we build neural networks to decode our own neural networks...

The only reason I paid any attention was because of an impressive demo they put out a few months back. https://youtu.be/6tA_VvHP0-s Still, who knows at this point.

ok, you gotta be a little more subtle with the sarcasm there, lol

Lol, I totally called this.

Or.. we just greatly overestimated what our brains were doing all along..

Similar work DiscoGAN https://github.com/SKTBrain/DiscoGAN

this really is a great vision that is both plausible and achievable within our lifetimes

can we eventually apply style transfer to speech? I'd like to hear all audio narration in the voice of David Attenborough.

Ugh Matlab. Someone needs to rewrite it in Julia