Machine learning approaches like classifiers, regressions, and

cluster analysis can help you navigate raw data sets that need customized solutions.

In computer science and

software engineering, doing custom work like this is often called low level

because you're working with the most basic pieces of the problem.

But most approaches to machine learning can be described using statistical

analysis and math.

Which means that some of the components for a spam filter that classifies

something as spam or not spam can be reapplied to another similar problem, like

classifying different types of zoo animals based on their physical appearance.

For this reason, there are many high level machine learning frameworks

that already have all the low level code written so

you can just plug your code and your data into pre-existing models.

Later in this course we're going to use a free one called scikit-learn.

Let's hop into a web browser and take a quick look at the big

machine learning frameworks that are already out there.

First up is scikit-learn.

Scikit-learn is free to use and it's written in Python.

It allows you to utilize some of the models we've already discussed

in just a few lines of code.

Right on the home page, you can see it features tools for

classification, regression, clustering and more.

This is a good choice for many different types of projects,

especially on very customized problem domains, because it's all open-source.

Next is TensorFlow.

TensorFlow is another free open-source Python project with

a different approach to machine learning that uses what are called Tensors,

which can be thought of as multi-dimensional arrays.

Then operations can be performed on Tensors, and

the results can be visualized in graphs.

This is somewhat of a departure from the machine learning approaches I mentioned

previously.

But it's worth exploring the website and

understanding what TensorFlow has to offer.

Next, is Amazon Web Services and their machine learning products,

which is more of a cloud based platform than a framework.

If we scroll down a bit there's a section that lists some

API services and that includes image recognition,

language translation, tools to create chat bots and more.

This can be a good choice for many different problems, but especially if your

problem domain can be neatly categorized into one of these high level APIs.

IBM Watson offers many high level products and services for machine learning.

They include common problem domains like chat bots and imagine recognition.

But also includes some others

that focus on natural language processing and emotional intent.

Similar to the others, this is a great choice for

many different types of problems.

And it can give you a big head start when you need to

utilize their higher level features that would be difficult to create on your own.

There are many more frameworks out there so

check the notes associated with this video for more resources.

As you've probably gathered, not all machine learning frameworks are the same.

And in fact, you could argue that not all of these are really frameworks,

but also software libraries or cloud based platforms.

The semantics and scopes of these tools varies but as you gain more experience and

encounter different types of machine learning problems,

it's important to know that there are many resources available to you.