lucidrains

Ping me too, I'd be happy to help build whatever

in some way, we are just piecing together representations of each other from the photons that fly into our eyes. so maybe 'reality' is only as good as these photons that we receive anyhow.

Discogan is amazing and the name, lol

Found the philosopher lol

you may need to train some powerful discriminator networks to do that job instead of relying on the one in your head soon..

pretty cool. i'm going to try char-rnn with rwa some time

Oh yea, I'm confusing it with INTERNIST. https://en.wikipedia.org/wiki/Internist-I

Yes, the explainability of expert systems is the only thing going for it.

Yes, there are issues with both, but we are really debating different solutions for different problems. For visual recognition, there is no doubt in my mind that deep learning is king.

I am assuming you are referring to the expert system used for infectious diseases. They performed well, but could not adapt to the constantly changing guidelines, medications. Data input was inefficient back in the days of terminals. It took about 5 thousands rules to be on par with a junior infectious disease doctor if I remember my studies on this subject.

The deep neural net visual diagnostics are different. They are learned on pure pixels as we would from photons striking our retina, signals traveling all the way back to our visual cortex for learning. There is no assembling of thousands of rules here and therefore the system is less brittle.

These new systems get more powerful with more data given to them. Expert systems required humans to craft rules from the data, and therefore required constant maintenance and is fallible to human error.

So yes, some of the barriers are definitely technological in nature.

Comparing apples and oranges here. Mycin is an expert system dealing with changing rulesets with A LOT of manual teaching. The current papers deals with computers discerning visual patterns by itself.

This is why we need a platform for these models asap. I would totally download this app today and use it regardless of what the FDA thinks.

They should do a Libratus vs Deepstack tournament https://arxiv.org/abs/1701.01724

So when are we going to see the paper where we use an RL net to speed up another RL net for discovering a neural architecture for learning how to do gradient descent (by gradient descent)?

I'm interested! Your blog posts are great! :)

second this. mobile development is way too expensive for a single individual like you

Nice job! I want to see another RNN net generate the yaml configs after we have collected enough of them for training. :)

Schmidhuber cracks some hilarious jokes when he is on stage.

"The other day I gave a talk and there was just a single person in the audience, a young lady. I said young lady it's very embarrassing but apparently today I'm going to give this talk just to you. She said okay but please hurry I gotta clean up here."

Yea the analogy doesn't hold. I was simply probing at the author's criticism (or fear) of deep learning as a flawed approach given the resulting model is pretty opaque.

To be honest, I would have felt the same way two years ago. Seeing all these recent advances in the field has slowly changed my mentality.

250$ LIDAR is on the horizon http://driverless.wonderhowto.com/news/quanergys-new-250-sol...

Fun thought experiment.

An alien race landed on earth and demands to play a game of Go. We only get to play one game with them. If they win, our planet is destroyed.

Who would you trust to play for the human race if this scenario happened tomorrow? Lee Sedol or AlphaGo? Remember that we do not completely understand how AlphaGo reasons, it is still a black box to us.

Video: https://www.youtube.com/watch?v=7jS4AuPnmyg

"Audi and NVIDIA developed an Audi Q7 piloted driving concept vehicle, which uses neural networks and end-to-end deep learning. Demo track at CES 2017 in Las Vegas."

This is why I love hackernews. Reading this tonight, thanks Eric :)

Same topic presented at KDD, with timestamp that cuts to the results.

https://www.youtube.com/watch?v=x1kf4Zojtb0&t=1h8m46s

Other equally exciting papers that relates to learning to learn in DL.

"Neural Architecture Search with Reinforcement Learning"

https://arxiv.org/abs/1611.01578

"RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning"

https://arxiv.org/abs/1611.02779

"Designing Neural Network Architectures using Reinforcement Learning"

https://arxiv.org/abs/1611.02167

this paper still consistently blows my mind whenever it is brought up. the future is clearly headed for complete end-to-end learning systems, maybe even with learning to learn methods. https://youtu.be/x1kf4Zojtb0?t=1h4m54s

Stories like these make me a disbeliever of basic income.

for some reason, the idea of autonomous bots crawling around the internet also unsettles me. i guess it really depends on what kind of rewards you train it for.

absolutely dude.. for example, this paper just popped up in the last week https://arxiv.org/abs/1611.02167

just toys? https://en.wikipedia.org/wiki/Deep_learning#Applications

we may end up generating our own cthulhu