Applications of Machine Learning


(popping) (upbeat music) – Everybody now deals
with machine learning. Drives my wife crazy sometimes
because recommender systems, right, this is one of
the first applications. Netflix, my wife gets really
upset because if I go in and sign in as her and watch a movie all of a sudden she’s
watching action movies and not watching some of the deep philosophical movies she likes to watch. But recommender systems are certainly one of the major applications. Classifications, cluster
analysis, trying to find some of the marketing
questions from 20 years ago, market basket analysis, what goods tend to be bought together. That was computationally a
very difficult problem, I mean we’re now doing that all the
time with machine learning. So predictive analytics is
another area of machine learning. We’re using new
techniques to predict things that statisticians
don’t particularly like. Decision trees, Bayesian
Analysis, naive Bayes, lots of different techniques. The nice thing about them is
that in packages like R now, you really have to understand
how these techniques can be used and you don’t have to
know exactly how to do them but you have to understand
what their meanings are. Precision versus recall and
the problems of over sampling and over fitting so you can,
someone who knows a little about data science can
apply these techniques but they really need to
know, maybe not the details of the technique as much as
how, what the trade-offs are. And I’ll give a plug
for Foster Provost’s book where he’s actually written a whole book basically telling practitioners how to use all of these new machine
learning techniques. (music) I have two sprinkler
systems running right now, one in Maine and one in New Jersey, that talk to me and tell me
what’s happening and I can turn them on and off and
program them and whatever. Yes, we already have
refrigerators that will tell you, scan things that tell you
what’s in them and stuff. Kettles, there’s a little
problem with heat there, I’m not so sure about kettles
but many, many, many devices now furnaces, I mean any kind
of device you put in the home is gonna generate data. I have my thermostat,
I mean I can tell you what the temperature is
in my house right now if I wanted to, I can turn it up and down, I can turn lights on and
off and I’m just, my wife won’t let me go very far with this because it drives her totally crazy. Totally crazy. I could right now connect to
the camera in my living room and talk to my wife but if
I did I would probably have the door locked when I get home. But there are people out there
that have their total lives totally generating data about them. My fitbit, which I haven’t had very long, this is collecting lots of data about me. And it could collect a lot more that I can feed to my doctor. (music) One of the cool things that’s going on now is these peer-to-peer networks, what we call ZigBee, these ZigBee networks that are fairly very low frequency but a ZigBee device can run on a battery for a couple of years,
they’re only this big, and they can talk to each other so they can form a mesh network. Just throw them around the building and they’ll talk to each other and one of them will
connect to the internet and push its data out. (music)

Leave a Reply

Your email address will not be published. Required fields are marked *