Inferring Algorithmic Patterns with Stack

Re:Inferring Algorithmic Patterns with Stack by andrewtbham on Saturday September 05, 2015 @12:21PM (#10175220)

Reasons this high has probability of credibility: Research probably used on Facebook digital assistant M. Tomas Mikolov, the author of word2vec. Paper with source code.

http://arxiv.org/pdf/1503.01007.pdf

https://github.com/facebook/Stack-RNN

[ Parent | on HN ]

Re:Inferring Algorithmic Patterns with Stack by ching_wow_ka on Saturday September 05, 2015 @12:25PM (#10175231)

I doubt that it's used in M.

"Why not just build M with neural nets from the beginning? Without the right data, neural nets couldn’t provide a service much more powerful than, well, Siri, and Wit.ai’s tech can get things started with relatively little data. “This is a good way to bootstrap. With a few thousand data-points, you can start to build a model,” Lebrun says. “Then, using this model, you get more data, and once you have about a million data points, you go to Yann and get some deep learning.”" [1]

[1] http://www.wired.com/2015/08/how-facebook-m-works/

[ Parent | on HN ]

Re:Inferring Algorithmic Patterns with Stack by andrewtbham on Saturday September 05, 2015 @12:56PM (#10175338)

That was a month ago... I'm sure they have some data by now or at least a plan on what to do once they get more data.

[ Parent | on HN ]

Re:Inferring Algorithmic Patterns with Stack by Irishsteve on Sunday September 06, 2015 @05:56AM (#10177228)

They are probably using M to get more data to learn from.

[ Parent | on HN ]