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

From: Laslo Hunhold <dev_AT_frign.de>
Date: Sat, 24 Mar 2018 13:00:25 +0100

On Sat, 24 Mar 2018 12:01:02 +0100
ssd_AT_mailless.org wrote:

Dear ssd,

> 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.

most of the deep learning folks don't know what the hell they're doing
and it will cost us big time in the near or far future.
Just throwing data at a problem you do not understand will get you
better results but won't solve the fundamental issue of not
understanding it.

With best regards

Laslo

-- 
Laslo Hunhold <dev_AT_frign.de>
Received on Sat Mar 24 2018 - 13:00:25 CET

This archive was generated by hypermail 2.3.0 : Sat Mar 24 2018 - 13:12:20 CET