[visarga]

Deep mind is breaking new ground in number of directions. For example, "Decoupled Neural Interfaces using Synthetic Gradients" is simply amazing - they can make training a net async and run individual layers on separate machines by approximating the gradients with a local net. It's the kind of thing that sounds crazy on paper, but they proved it works.

Another amazing thing they did was to generate audio by direct synthesis from a neural net, beating all previous benchmarks. If they can make it work in real time, it would be a huge upgrade in our TTS technology.

We're still waiting for the new and improved AlphaGo. I hope they don't bury that project.

[shostack]

I'm not super knowledgeable about the space, but would the audio generation you mentioned be what is needed to let their Assistant communicate verbally in any language, any voice, add inflections, emotion, etc. without needing to pre-record all the chunks/combinations?

[outsideline]

Decoupled Neural Interfaces using Synthetic Gradients is a fancy name for the electro-chemical gradient that lies outside the cell wall of neurons : https://en.wikipedia.org/wiki/Electrochemical_gradient

It's decoupled yet stores transient local information regarding previous neuron activity.

Another bio-inspired copy-pasta.

[vintermann]

You should absolutely get a job doing it, if you think bio-inspired copy-pasta is all it takes. May I recommend Numenta?

[dj-wonk]

Please choose derogatory phrases like 'copy pasta' intentionally and carefully.

Many algorithms are bio-inspired -- good artists borrow, the best steal.