benibraz

Surprised to see that no one mentioned https://vespa.ai/ the best alternative to vector DB imho

Is this a simplified interpretation of GNNs? because I couldn't find a reference for that.

EDIT: found it! https://arxiv.org/pdf/1609.02907.pdf

What do you mean by 'the best'? Deeper architectures are popular because they quiet easy to train. They do work well in practice on many tasks (especially vision) but they have their limits.

Infinite wide networks are a newly active field and has recently shown some promising results, theoretically [1, 2] and empirically [3].

[1] https://arxiv.org/abs/2001.06931 [3] https://arxiv.org/abs/1806.07572 [2] https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-w...

A wide enough NN can represent any arbitrary binary function, but it's not obvious that one can learn it.

I find the technique very similar to the one presented in [1] from 2018, and I can't seem to find a ref to this paper in theirs.

Another interesting and very related paper [2] that they fail to mention also shows improvement in training time (epochs) with dynamic pruning

And for the ones who wondered how far this is going back time I suggest you to read this one [3]

[1] https://www.nature.com/articles/s41467-018-04316-3

[2] https://arxiv.org/abs/1608.04493

[3] https://papers.nips.cc/paper/323-generalization-by-weight-el...

He just uploaded the second part of this series an hour ago: https://www.youtube.com/watch?v=V-1RhQ1uuQ4

Very nice tool, thank you very much that. This is why is love HN

Yeah, this is actually quite funny. You can also watch it on iTunes. Are Amazon and Apple exceptions with respect to selling your information? (I'm genuinely asking)