1817
Automation (lemmy.world)
you are viewing a single comment's thread
view the rest of the comments
[-] OsrsNeedsF2P@lemmy.ml 8 points 4 months ago

While I believe that, it's an issue with the training data, and not the hardest to resolve

[-] dondelelcaro@lemmy.world 56 points 4 months ago

Maybe not the hardest, but still challenging. Unknown biases in training data are a challenge in any experimental design. Opaque ML frequently makes them more challenging to discover.

[-] nova_ad_vitum@lemmy.ca 25 points 4 months ago* (last edited 4 months ago)

The unknown biases issue has no real solution. In this same example if instead of something simple like snow in the background, it turned out that the photographs of wolves were taken using zoom lenses (since photogs don't want to get near wild animals) while the dog photos were closeup and the ML was really just training to recognize subtle photographic artifacts caused by the zoom lenses, this would be extremely difficult to detect let alone prove.

[-] dondelelcaro@lemmy.world 4 points 4 months ago

Exactly.

The general approach is to use interpretable models where you can understand how the model works and what features it uses to discriminate, but that doesn't work for all ML approaches (and even when it does our understanding is incomplete.)

[-] Mirodir@discuss.tchncs.de 13 points 4 months ago

So is the example with the dogs/wolves and the example in the OP.

As to how hard to resolve, the dog/wolves one might be quite difficult, but for the example in the OP, it wouldn't be hard to feed in all images (during training) with randomly chosen backgrounds to remove the model's ability to draw any conclusions based on background.

However this would probably unearth the next issue. The one where the human graders, who were probably used to create the original training dataset, have their own biases based on race, gender, appearance, etc. This doesn't even necessarily mean that they were racist/sexist/etc, just that they struggle to detect certain emotions in certain groups of people. The model would then replicate those issues.

[-] Grandwolf319@sh.itjust.works 1 points 4 months ago

I bet ML would also think people with glasses are smarter or some dumb thing like that.

[-] merc@sh.itjust.works 7 points 4 months ago

Yes, "Bias Automation" is always an issue with the training data, and it's always harder to resolve than anyone thinks.

[-] StaticFalconar@lemmy.world 6 points 4 months ago

Old data adage. Garbage in, garbage out.

[-] Knock_Knock_Lemmy_In@lemmy.world 1 points 4 months ago

Actually, in this case the data sounds pretty clean.

this post was submitted on 24 Jun 2024
1817 points (99.3% liked)

Lemmy Shitpost

26697 readers
3240 users here now

Welcome to Lemmy Shitpost. Here you can shitpost to your hearts content.

Anything and everything goes. Memes, Jokes, Vents and Banter. Though we still have to comply with lemmy.world instance rules. So behave!


Rules:

1. Be Respectful


Refrain from using harmful language pertaining to a protected characteristic: e.g. race, gender, sexuality, disability or religion.

Refrain from being argumentative when responding or commenting to posts/replies. Personal attacks are not welcome here.

...


2. No Illegal Content


Content that violates the law. Any post/comment found to be in breach of common law will be removed and given to the authorities if required.

That means:

-No promoting violence/threats against any individuals

-No CSA content or Revenge Porn

-No sharing private/personal information (Doxxing)

...


3. No Spam


Posting the same post, no matter the intent is against the rules.

-If you have posted content, please refrain from re-posting said content within this community.

-Do not spam posts with intent to harass, annoy, bully, advertise, scam or harm this community.

-No posting Scams/Advertisements/Phishing Links/IP Grabbers

-No Bots, Bots will be banned from the community.

...


4. No Porn/ExplicitContent


-Do not post explicit content. Lemmy.World is not the instance for NSFW content.

-Do not post Gore or Shock Content.

...


5. No Enciting Harassment,Brigading, Doxxing or Witch Hunts


-Do not Brigade other Communities

-No calls to action against other communities/users within Lemmy or outside of Lemmy.

-No Witch Hunts against users/communities.

-No content that harasses members within or outside of the community.

...


6. NSFW should be behind NSFW tags.


-Content that is NSFW should be behind NSFW tags.

-Content that might be distressing should be kept behind NSFW tags.

...

If you see content that is a breach of the rules, please flag and report the comment and a moderator will take action where they can.


Also check out:

Partnered Communities:

1.Memes

2.Lemmy Review

3.Mildly Infuriating

4.Lemmy Be Wholesome

5.No Stupid Questions

6.You Should Know

7.Comedy Heaven

8.Credible Defense

9.Ten Forward

10.LinuxMemes (Linux themed memes)


Reach out to

All communities included on the sidebar are to be made in compliance with the instance rules. Striker

founded 1 year ago
MODERATORS