Join the conversation
Log in or create an account to leave a comment
Log In
[Downey] The team uses the same kind of machine learning that allows us to organize our photos or tag friends on social media, image recognition. First, models are trained using tagged images of things like cats or dogs. After looking at thousands of examples, the algorithm learns to identify new images without any human help. For the retinopathy project, over 100,000 eye scans were graded by eye doctors who rated each eye scan on a scale from one to five, from healthy to diseased. These images were then used to train a machine learning algorithm. Over time, the AI learned to predict which eyes showed signs of disease. [Dr. Lily Peng]
This is the assistant's view where the model's predictions are actually projected on the original image, and it's picking up
the pathologies very nicely
This is the assistant's view where the model's predictions are actually projected on the original image, and it's picking up
the pathologies very nicely
Full Transcript
00:00:01.000 --> 00:00:03.803
[Downey] The team
uses the same kind
of machine learning
00:00:03.836 --> 00:00:06.172
that allows us
to organize our photos
00:00:06.206 --> 00:00:08.174
or tag friends
on social media,
00:00:08.208 --> 00:00:10.944
image recognition.
00:00:10.977 --> 00:00:12.512
First, models are trained
00:00:12.545 --> 00:00:15.949
using tagged images of things
like cats or dogs.
00:00:15.982 --> 00:00:18.001
After looking at
thousands of examples,
00:00:18.084 --> 00:00:21.254
the algorithm learns
to identify new images
00:00:21.287 --> 00:00:22.889
without any human help.
00:00:22.922 --> 00:00:25.292
For the retinopathy project,
00:00:25.325 --> 00:00:27.393
over 100,000 eye scans
00:00:27.427 --> 00:00:28.928
were graded
by eye doctors
00:00:28.962 --> 00:00:32.465
who rated each eye scan
on a scale from one to five,
00:00:32.498 --> 00:00:34.067
from healthy to diseased.
00:00:34.001 --> 00:00:35.735
These images were then used
00:00:35.768 --> 00:00:38.998
to train a machine
learning algorithm.
00:00:38.104 --> 00:00:40.706
Over time,
the AI learned to predict
00:00:40.074 --> 00:00:43.342
which eyes showed signs
of disease.
00:00:43.376 --> 00:00:45.745
[Dr. Lily Peng]
This is the assistant's view
00:00:45.779 --> 00:00:47.213
where the model's predictions
00:00:47.247 --> 00:00:50.075
are actually projected
on the original image,
00:00:50.784 --> 00:00:54.554
and it's picking up
the pathologies very nicely.
Want This Clip in HD?
Upgrade for HD/4K downloads and unlimited access. Upgrade now →
Movie Summary
The Age of A.I. is a 8 part documentary series hosted by Robert Downey Jr. covering the ways Artifial Intelligence, Machine Learning and Neural Networks will change the world.