And when we're going about this, our goals here are to minimize the amount of

prerequisite knowledge that you have to have to understand what we're presenting,

while maximizing the ability for you to actually develop and

deploy these methods on new problems that are of interest to you.

And when we're thinking about this, we're going to be presenting concepts

at this very intuitive level that's grounded in these case studies.

So who might you be?

Well, when we're thinking about the target audience,

we're thinking about software engineers who are interested in machine learning.

We're thinking about scientists who might want to become data scientists.

And we're thinking about lots and lots and lots of other people who have some math,

some programming experience, and want to be able to analyze data and

do fun things with it, so just data enthusiasts who want to learn more about

machine learning and how to derive intelligence from data.

Okay.

So I said that we're assuming you have some math and

some programming background, so let's talk about this in a little bit more detail.

In terms of the math background,

we're assuming that you have some basic calculus knowledge.

So that's understanding the notion of derivatives and

how they're computed and basic linear algebra.

So you guys should know what a vector is, what a matrix is, and

how to multiply matrices.

But in these cases, we're really as

often as possible going to present things at the most intuitive level.

Even if we could write down an equation in terms of matrices and matrix multiplies,

we're going to try and add as many visual aids as possible to provide you with that

intuition, so that if you're only marginally comfortable with these ideas,

I do suggest that you go brush up on these concepts.

But, again, we're going to try and

provide the intuition that we described as part of our motto.