|
you're gonna die suddenly and violently anyway, so it ultimately doesn't matter if it's at the hands of a guy who had a sip of beer 30 minutes ago before driving, or by an idiot neural net programmed by a guy who skimmed a deep learning tutorial a day before the deadline that doesn't understand the concept of "things moving in both space and time"
|
# ¿ Nov 14, 2019 11:43 |
|
|
# ¿ May 10, 2024 10:56 |
|
return0 posted:why is clustering some data so hard, it’s 2019 ugh have you tried adding more bias to your training set
|
# ¿ Dec 3, 2019 01:04 |
|
is fortran still faster than c for some types of numeric calculations for deeply technical yet tedious reasons?
|
# ¿ Dec 5, 2019 02:00 |
|
Suspicious Dish posted:dumb serious question. why do we use nonlinear functions instead of linear ones if they're all dumb poo poo like ReLU which seems like it barely works. I guess second question: is there any theoretical basis for why ReLU works at all? i thought the state of the art with why some activation functions work better than other functions in some cases is essentially
|
# ¿ Dec 15, 2019 08:19 |
|
it's a pity that nlp and cv have fallen to the ml gremlins
|
# ¿ Jan 3, 2020 03:20 |
|
is breast cancer such a popular target because the image sets are large and well-labelled?
|
# ¿ Jan 5, 2020 04:51 |
|
animist posted:if you're willing to put the time in found the problem. if neural nets don't give me results easily and with no thought on my part, what's the point??
|
# ¿ Apr 29, 2020 01:46 |
|
animist posted:also tbh if you're trying to understand data I'd reach for visualizations wayyy before ML because ML will just spit black boxes back at you. that's because I like to understand things tho sounds like you don't have the right mindset for doing ml
|
# ¿ Jun 6, 2020 00:00 |
|
that thing is great at generating white people faces though. top marks there
|
# ¿ Jun 21, 2020 23:31 |
|
https://twitter.com/futurism/status/1278701098627469317
|
# ¿ Jul 3, 2020 01:41 |
|
animist posted:the list of words is from WordNet, which is a linguistic dataset from the 80s. and apparently includes racial slurs?? i can only aspire to be as lazy as an ml researcher
|
# ¿ Jul 6, 2020 21:56 |
|
the end goal is simply "get more funding for the next three years"
|
# ¿ Jul 7, 2020 08:51 |
|
did he at least look ashamed when he said that
|
# ¿ Jul 18, 2020 06:47 |
|
Sagebrush posted:yeah it is definitely one of the worst "AI" systems i've seen, as measured by how obvious/natural its responses are. whatever it's fitting to, it clearly isn't what humans use. it's baffling how little effort they put into validation. like, they clearly didn't try at all at least, that's what i'd be saying if this wasn't a clear and obviously viral marketing gimmick designed to draw attention to their product. "look how bad this is!!!" we gleefully yell as we give them clicks
|
# ¿ Jul 29, 2020 01:45 |
|
Carthag Tuek posted:training a tank with starcraft AI is some tesla-tier bullshit Glorgnole posted:just using the algorithm is the whole point of the exercise, totally independent from how effective, practical, or appropriate it is
|
# ¿ Jul 30, 2020 01:24 |
|
|
# ¿ Aug 7, 2020 23:05 |
|
ah, the trick there is that no one cares about criminals
|
# ¿ Aug 26, 2020 01:05 |
|
gotta agree with this
|
# ¿ Sep 27, 2020 00:17 |
|
|
# ¿ May 10, 2024 10:56 |
|
morally obligated to lie on this one
|
# ¿ Apr 1, 2021 01:59 |