linear regression.

So, that's linear regression.

linear regression for classification problems.

This is non linear.

And then, is this linear or non linear?

So, here's our linear regression algorithm.

linear regression isn't a good idea .

So linear regression works well if the data is approximately linear, but there are many examples when linear regression performs poorly.

So that's linear regression with gradient descent.

And thus, using linear regression this way.

Linear regression? Do we compute confidence intervals?

They ask us, is this function linear or non linear?

Free hand Draw non linear lines

So outliers are particularly bad for linear regression.

Our first learning algorithm will be linear regression.

You now know about linear regression and gradient descent.

And let's say you've implement and regularize linear regression.

This model is called linear regression or this, for example, is actually linear regression with one variable, with the variable being x.

In this case, it's not, it's non linear.

Thrun In this question I quiz you about linear regression.

Right? This was our objective function for the linear regression.

linear regression for fitting a straight line to our data.

This line over here is linear regression to the data.

And then you have this notion of whether it is linear or non linear.

So that also makes this a non linear equation.

We already have linear regression and we have logistic regression, so why do we need, you know, neural networks?

If they're not, then we're dealing with a non linear function.

So to have the y squared, that makes it non linear.

Then linear regression tries to fit a line that best describes the data.

Are there closed form solutions of the type we found for linear regression?

So this is going to be my overall objective function for linear regression.

Up to this point, I've just been showing you linear relationships, this regression

The minimizing of loss is used for linear regression of a new regression problem, and you can write it as follows

That's our gradient descent algorithm, which should be familiar, and you see the linear linear regression model with our linear hypothesis and our squared error cost function.

And why a linear function? Well, sometimes we'll want to fit more complicated, perhaps non linear functions as well.

Now, all of the sudden, I have a non linear differential equation.

To define linear regression, we need to understand what we are trying to minimize.

And this seems a pretty bad thing for linear regression to have done, right?

And, just to give this another name, this is also called multivariate linear regression.

And I'll quickly review the linear algebra you need in order to implement and use the more powerful versions of linear regression.

Now the second thing we have to figure out is this linear or is this a non linear differential equation?

Here's a usual hypothesis of linear regression and if you want to compute H of

So, applying linear regression to a classification problem usually isn't, often isn't a great idea.

Red is what represents the solutions to this non linear system of equations.

For such situations there is a model called logistic regression, which uses a slightly more complicated model than linear regression, which goes as follows .