So if you apply the rule over here, if you were to start at A as your W zero, then your gradient is negative.

Maximum gradient

But the easiest way I always do is to draw these arrows and say, OK, when I increase x, y is decreasing.

Now, they tell us what the slope of this line is.

Draw scrollbar bevel

And essentially, the apartments cover the parking.

It sends out that at local optimum your derivative would be equal to zero.

Increase

Sixpercent grade, fast greens, breaks to the left.

increasing Y

In B, it's about zero.

Byline two should read Mini prod forecast increase choco ration, April 1984 , from 20g to 25g per week.

How can we describe this mathematically?

So at any point, the gradient is a vector.

Enhancing grav plating.

Now, my derivative term, d, d theta one j of theta one, when evaluated at this point, gonna look at right.

That's where the derivative is.

And it turns out there are sometimes other versions of gradient descent that are not batch versions but instead do not look at the entire traning set but look at small subsets of the training sets at the time, and we'll talk about those versions later in this course as well.

India is going to have a lot of young people with a demographic dividend for the next 30 years.

And, you notice that my line changed a little bit.

We'll grow by six cities of 12 million people a year for the next 30 years.

Once we start getting into the positive numbers, we just explode.

What we're going to do is apply gradient descent to minimize our squared error cost function.

But for now, using the algorithm you just learned, now we're using batch gradient descent, you now know how to implement gradient descent, or linear regression.

What happened is a market that didn't exist all things have just come together, and it's become the year of online education, or it's become the year of the network, or it's become the year of the mobile phone or smart phone.

Canaries used to be used as kind of biosensors in mines.

Adapt maximum gradient

How can we optimize these two terms over here?

The road across the mountain was narrow, and what's more, it was a steep slope.

It makes sense because it's a downward sloping line, but it's not too steep.

The gradient with respect to W0 is very similar.

So how much do we have to go to from 150 to 225?

Here is a prototypical loss function and the method for interation will be called gradient descent.

I should say so, yes. Choco rations going up.

It is able to move around its environment.

It's on very steep ground.

You do this until you find yourself with what's called a local minimum, where B resides.

So, income goes up, then that increases demand.

I see now a 15 over here for this maze where you have to go down,

So it's interesting.

If someone did this enough, then this would increase the supply of apples here so supply would increase in this market and in this market the demand will increase because there's someone who keeps buying in this market and selling into that market

We already know that this has a closed form solution, but just for the fun of it, let's look at gradient descent.

And these expressions look nasty, but what it really means is we subtract an expression like this every time we do gradient descent from W1 and an expression like this every time we do gradient descent from W0, which is easy to implement, and that implements gradient descent.

And so if income goes up for this laptop, the demand will increase.

Is it linear or nonlinear?