this post was submitted on 19 Dec 2023
28 points (65.9% liked)
Autism
6935 readers
92 users here now
A community for respectful discussion and memes related to autism acceptance. All neurotypes are welcome.
We have created our own instance! Visit Autism Place the following community for more info.
Community:
Values
- Acceptance
- Openness
- Understanding
- Equality
- Reciprocity
- Mutuality
- Love
Rules
- No abusive, derogatory, or offensive post/comments e.g: racism, sexism, religious hatred, homophobia, gatekeeping, trolling.
- Posts must be related to autism, off-topic discussions happen in the matrix chat.
- Your posts must include a text body. It doesn't have to be long, it just needs to be descriptive.
- Do not request donations.
- Be respectful in discussions.
- Do not post misinformation.
- Mark NSFW content accordingly.
- Do not promote Autism Speaks.
- General Lemmy World rules.
Encouraged
- Open acceptance of all autism levels as a respectable neurotype.
- Funny memes.
- Respectful venting.
- Describe posts of pictures/memes using text in the body for our visually impaired users.
- Welcoming and accepting attitudes.
- Questions regarding autism.
- Questions on confusing situations.
- Seeking and sharing support.
- Engagement in our community's values.
- Expressing a difference of opinion without directly insulting another user.
- Please report questionable posts and let the mods deal with it. Chat Room
- We have a chat room! Want to engage in dialogue? Come join us at the community's Matrix Chat.
.
Helpful Resources
- Are you seeking education, support groups, and more? Take a look at our list of helpful resources.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
A full 100% sounds weird. It means complete overlap with the ASD assessment which itself isn't bulletproof. Weird like there were some mistakes in the data. E.g. all ASD pictures taken on the same day and getting a date timestamp, "ASD" written in the metadata or filename, or different light in different lab.
I didn't see any immediate problems in the published paper, but if these were my results I'd be to worried to publish it.
It sounds like the model is overfitting the training data. They say it scored 100% on the testing set of data which almost always indicates that the model has learned how to ace the training set but flops in the real world.
I think we shouldn’t put much weight behind this news article. This is just more overblown hype for the sake of clicks.
The article says they kept 15% of the data for testing, so it's not overfitting. I'm still skeptical though.
I’m pretty sure it’s possible to overfit even with large testing sets.
The paper mentioned how the images were processed (chopping 10% off some to remove name, age, etc). But all were from the same centre and only pixel data was used. Given the other work referenced on retinal thinning in ASD disorders, maybe it is a relatively simple task for this kind of model. But they do say using multi-centre images will be an important part of the validation. It’s quite possible the performance would drop away when differences in camera, etc. are factored in.