In previous videos, we talked

about the gradient descent algorithm

and talked about the linear
regression model and the squared error cost function.
In this video, we're going to
put together gradient descent with
our cost function, and that
will give us an algorithm for
linear regression for fitting a straight line to our data.
So, this is
what we worked out in the previous videos.
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.
What we're going to do is apply
gradient descent to minimize
our squared error cost function.
Now, in order to apply
gradient descent, in order
to write this piece of
code, the key term
we need is this derivative term over here.
So, we need to figure out
what is this partial derivative term,
and plug in the
definition of the cost
function J, this turns
out to be this "inaudible"
equals sum 1 through M of
this squared error
cost function term, and all
I did here was I just
you know plugged in the definition of
the cost function there, and simplifying
little bit more, this turns
out to be equal to, this
"inaudible" equals sum 1 through M
of tetha zero plus tetha one, XI
minus YI squared.
And all I did there was took
the definition for my hypothesis
and plug that in there.
And it turns out we need
to figure out what is
the partial derivative of two
cases for J equals
0 and for J equals 1 want
to figure out what is this
partial derivative for both the
theta(0) case and the theta(1) case.
And I'm just going to write out the answers.
It turns out this first term simplifies
to 1/M, sum over
my training set of just
that, X(i)- Y(i).
And for this term, partial derivative
with respect to theta(1), it turns
out I get this term: -Y(i)<i>X(i).</i>
Okay.
And computing these partial
derivatives, so going from
this equation to either
of these equations down there, computing
those partial derivative terms requires some multivariate calculus.
If you know calculus, feel free
to work through the derivations yourself
and check take the derivatives
you actually get the answers that I got.
But if you are less
familiar with calculus you don't
worry about it, and it
is fine to just take these equations
worked out, and you
won't need to know calculus or
anything like that in order to
do the homework, so to implement gradient descent you'd get that to work.
But so, after these definitions,
or after what we've worked
out to be the derivatives, which
is really just the slope of
the cost function J. We
can now plug them back into
our gradient descent algorithm.
So here's gradient descent, or
the regression, which is going
to repeat until convergence, theta 0
and theta one get updated as,
you know, the same minus alpha
times the derivative term.
So, this term here.
So, here's our linear regression algorithm.
This first term here that
term is, of course, just
a partial derivative of respective
theta zero, that we worked on in the previous slide.
And this second term here,
that term is just
a partial derivative with respect to
theta one that we worked out on the previous line.
And just as a quick reminder,
you must, when implementing gradient descent,
there's actually there's detail that, you
know, you should be implementing
it so the update theta zero and theta one simultaneously.
So, let's see how gradient descent works.
One of the issues we solved
gradient descent is that it can be susceptible to local optima.
So, when I first explained gradient
descent, I showed you this picture
of it, you know, going downhill
on the surface and we
saw how, depending on where
you're initializing, you can end up with different local optima.
You know, you can end up here or here.
But, it turns out that
the cost function for gradient
of cost function for linear regression
is always going to be
a bow-shaped function like this.
The technical term for this
is that this is called a convex function.
And I'm not going
to give the formal definition for what
is a convex function, c-o-n-v-e-x, but
informally a convex function
means a bow-shaped function, you know, kind of like a bow shaped.
And so, this function doesn't
have any local optima, except
for the one global optimum.
And does gradient descent on
this type of cost function which
you get whenever you're using linear
regression, it will always convert
to the global optimum, because there are no other local optima other than global
optimum.
So now, let's see this algorithm in action.
As usual, here are plots of
the hypothesis function and of
my cost function J.
And so, let's see how
to initialize my parameters at this value.
You know, let's say, usually you
initialize your parameters at zero
for zero, theta zero and zero.
For illustration in this
specific presentation, I have
initialised theta zero at
about 900, and theta one at about minus 0.1, okay?
And so, this corresponds to H
over X, equals, you know,
minus 900 minus 0.1 x
is this line, so out here on the cost function.
Now if we take one
step of gradient descent, we end
up going from this point
out here, a little
bit to the down left
to that second point over there.
And, you notice that my line changed a little bit.
And, as I take another step
at gradient descent, my line on the left will change.
Right.
And I have also
moved to a new point on my cost function.
And as I think further step
is gradient descent, I'm going
down in cost, right, so
my parameter is following
this trajectory, and if
you look on the left, this corresponds
to hypotheses that seem
to be getting to be
better and better fits for the
data until eventually,
I have now wound up at the global minimum.
And this global minimum corresponds to
this hypothesis, which gives me a good fit to the data.
And so that's gradient
descent, and we've just run
it and gotten a good
fit to my data set of housing prices.
And you can now use it to predict.
You know, if your friend has a
house with a
size 1250 square feet, you
can now read off the value
and tell them that, I don't
know, maybe they can get
$350,000 for their house.
Finally, just to give
this another name, it turns out
that the algorithm that we
just went over is sometimes
called batch gradient descent.
And it turns out in machine
learning, I feel like us machine
learning people, we're not always
created has given me some algorithms.
But the term batch gradient descent
means that refers to the
fact that, in every step
of gradient descent we're looking
at all of the training examples.
So, in gradient descent, you
know, when computing derivatives, we're computing
these sums, this sum of.
So, in every separate
gradient descent, we end up
computing something like this, that
sums over our M training examples.
And so the term batch gradient
descent refers to the fact
when looking at the entire batch
of training examples, and again,
this is really, really not
a great name, but this is
what Machine Learning people call it.
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.
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.
So that's linear regression with gradient descent.
If you've seen advanced linear algebra
before so some you may
have taken a class with advanced
linear algebra, you might
know that there exists a solution
for numerically solving for the
minimum of the cost function
J, without needing to
use and iterative algorithm like gradient descent.
Later in this course we will
talk about that method as
well that just solves for the
minimum cost function J without
needing this multiple steps of gradient descent.
That other method is called normal equations methods.
And, but in case you
have heard of that method, it turns
out gradient descent will
scale better to larger data
sets than that normal equals
method and, now that
we know about gradient descent, we'll
be able to use it in
lots of different contexts, and we'll
use it in lots of different Machine Learning problems as well.
So, congrats on learning
about your first Machine Learning algorithm.
We'll later have exercises in
which we'll ask you to
implement gradient descent and
hopefully see these algorithms work for yourselves.
But before that I first
want to tell you in
the next set of videos, the
first want to tell you about
a generalization of the gradient descent
algorithm that will make
it much more powerful and I
guess I will tell you about that in the next video.