Henriapi illustrates this phenomenon as well.

Only instead of, you know, good and bad cancer tumors or benign or malignant tumors we instead have diabetes or not and so we will use that as a supervised, we will solve that as a Supervised Learning problem just like we did for the breast tumor data.

So on. So this example...

We didn't sequence his genome.

So 0 may denote the benign tumor and 1 positive class may denote a malignant tumor.

So, if angiogenesis is a tipping point between a harmless cancer and a harmful one, then one major part of the angiogenesis revolution is a new approach to treating cancer by cutting off the blood supply.

Walt, your tumor has shrunk by 80 percent.

Here's an example of a training set for a classification task for classifying a tumor as malignant or benign and notice that malignancy takes on only two values zero or no or one or one or yes.

Tumors?

That's another classification problem, and earlier we also talked about the example of classifying tumors as a cancerous malignant or as benign tumors.

The cancer.

What does that mean?

That's counterindicative for a hemorrhagic tumor.

Let's see you want to look at medical records and try to predict of a breast cancer as malignant or benign.

And a different set of patients, they look a little different, whose tumors turn out to be malignant, as denoted by the crosses.

Women suffer from that disease.

And one afternoon, I got a call from my doctor.

What is it? A tumor?

A few years ago I felt a lump on the side of my neck, and it was my turn in the MRI machine.

Mice with multiple myeloma, an incurable malignancy of the bone marrow, respond dramatically to the treatment with this drug.

However, in the presence of the tumor, now there are molecular scissors that can break this molecule apart right there at the cleavable site.

So this is a photograph of Henry, two weeks after he had a malignant cancer removed from the left side of his face his cheekbone, his upper jaw, his eye socket.

So given a data set like this, what the learning algorithm might do is throw the straight line through the data to try to separate out the malignant tumors from the benign ones and, so the learning algorithm may decide to throw the straight line like that to separate out the two classes of tumors.

In other words, I'm going to tell my patient that the tumor, sadly, has a 70 chance or a 0.7 chance of being malignant.

If someone discovers a breast tumor, a lump in their breast, a malignant tumor is a tumor that is harmful and dangerous and a benign tumor is a tumor that is harmless.

This is a little Bangladeshi girl from the east end of London who's got a huge malignant tumor on the right side of her face, which has already made her blind and which is rapidly growing and is going to kill her shortly.

But even before I peel that muscle away, you saw that there was a tumor underneath.

We r emoved a tumor fr om her brain.

Tom had a brain tumor.

When we put these two probes together ...

As you can see, it's blocking her vision.

The tumor's still small.

But there's been a significant reduction in the tumors.

Herbie

But often there is this intuition that the negative class is conveying the absence of something, like the absence of a malignant tumor, whereas one, the positive class, is conveying the presence of something that we may be looking for.

And now, boom, the tumor labels itself and it gets fluorescent.

So it's easy to see this tumor in the upper part of this fatty breast.

The molecule passes through and gets excreted.

That's impressive.

How about more targeted therapies for cancer?

Here is an example.

First of all, these electrodes are noninvasive.

You have a secondary tumor in the long bone of your arm

Not unless a tumor is made of glass.

But inevitably, these tumors progress towards being enormous, ulcerating tumors like this one here.