Re: [dev] What would a well-designed voice assistant program look like?

From: <ssd_AT_mailless.org>
Date: Sat, 24 Mar 2018 12:01:02 +0100

* Laslo Hunhold 2018-03-22 13:59
> When reflecting about a problem, it should be a priority to think about
> how it can be split up. In this case, we can talk about two problems,
> which combined, solve the "voice assistant" problem.
>
> 1) voice recognition
> 2) assistant

I'm sure that the deep learning folks will object: factorising in sub
problemswas yesterday; now we ge end-to-end. And indeed there are a few
examples where a field was swept by NN in short time (e.g. vision), at
least in terms of accuracy. This was done not by factorising the problem
better, but by solving it end-to-end with a lot of data.

--s
Received on Sat Mar 24 2018 - 12:01:02 CET

This archive was generated by hypermail 2.3.0 : Sat Mar 24 2018 - 12:12:19 CET