Graphical representation

Picture time let’s stop for a second and illustrate two situations in which machine learning and neural

networks come in handy.

You are probably wondering how a linear model can solve our cats and dogs photo problem.

Well it depends on the data.

Here is a scatterplot of a dataset consisting of animal photos.

The blue dots be the dogs is photos from one of our previous examples and the orange ones the cats a

linear model or a straight line can solve this problem fairly easily.

Everything below the line is one category.

While everything above it is the other in this situation we have a classification problem.

We are trying to classify the photos into dogs and cats.

Such a model is called a linear classifier.

It looks useful right.

Well that’s true because the data represented in the graph is linearly separable.

But what about this case we have only several categories but we can’t fit a straight line through them.

This data is not linearly separable.

Therefore we must use a non linear model.

Well we will learn how to handle such problems in the section where we will learn about deep neural

networks.

Finally to be true to our promises we will show you a regression picture.

Here is the graph of our apartment price example.

Each point represents an apartment a linear model explains the data.

Well right.

This is one of the well known linear relationships however different regression problems may not necessarily

be solved by a linear model.

Look at this graph for instance.

Totally not linear.

Once again thats a topic for deep neural networks for now you have learned the most fundamental modeling

block the linear model.

Thanks for watching.