Re:Baking with machine learning (2020)
by ipsum2 on Friday January 29, 2021 @05:33PM
(#25963641)
Seems like a linear model would work equally as well, without all the deep learning bits.
[ Parent
| on HN ]
You are right, but she is a GCP ML advocate, so her job is to distill this stuff down into blog posts or 45 minute talk tracks.
Re:Baking with machine learning (2020)
by mlthoughts2018 on Friday January 29, 2021 @06:13PM
(#25964081)
I normally agree, but this is clearly just for fun and for poking around with cloud tools. The author is not making claims about accuracy or anything, I think this post is not a good one for the stampede of “well actually...” ML approach bashing of HN. This is a nice post.
In my mind it stands in contrast to the SMART stats hard drive failure model post from a few days ago - that was an inappropriate approach AND the person was putting forward as actually being a valid analysis workflow & conclusion.
This post is obviously just for giggles, and it’s very good.
Yeah I know its just for fun, but you could use a single linear layer to demonstrate the same thing, and use the fancy TF tools as well.
Re:Baking with machine learning (2020)
by simonhughes22 on Friday January 29, 2021 @06:01PM
(#25963964)
My thoughts exactly. A DL for 100 row dataset seems like overkill (and likely overfits).
Re:Baking with machine learning (2020)
by refactor_master on Friday January 29, 2021 @05:54PM
(#25963889)
But tensorflow go brrrr
Agree no need for DL for this. Far more efficient models for this kind of use exist.