News for hackers. Stuff that matters.

A comment on Machine Learning. Parent comment

Re:Machine Learning by chrisan on Wednesday May 17, 2017 @08:44AM (#14357843)
How far away is ML from identifying everything in a picture?

For example if we could take a photo of Noah's Ark loading up every animal?

Do you just loop through each NN you have on each species?

[ Parent | on HN ]
Re:Machine Learning by nl on Wednesday May 17, 2017 @01:15PM (#14360511)
A single NN can predict more than one class of object. The ImageNet competition has 20,000 classes.

There's also image segmentation as another poster has pointed to.

In the case of FB face tagging, they'd have learn an embedding space for faces, and when a new image comes in they'd place it in the embedding space along with all the person's connections and find the nearest neighbors.

See https://arxiv.org/abs/1503.03832 or the implementation https://cmusatyalab.github.io/openface/

[ Parent | on HN ]
Re:Machine Learning by rjtavares on Wednesday May 17, 2017 @10:29AM (#14358738)
This seems to be what you are looking for: https://code.facebook.com/posts/561187904071636/segmenting-a...
[ Parent | on HN ]