As usual, let's recap what we've done this
week and preview next week's lecture.
We focused on learning or extracting
information from data such as figuring out
classes from data in an unsupervised
manner using clustering. Figuring out
rules from data using unsupervised rule
mining.
And we also took a look at big data, and
how just counting techniques work well if
you actually have lots of data, and our
unified f of x formulation helped up
understand clustering, rule mining as well
as classification in the same single
formulation.
We then turn to long data, high
dimensional data, and figure out how learn
classes and features in an unsupervised
model using hidden or latent techniques.
Next week, we'll continue our discussion
of learning a little bit because the
techniques will be very similar to the
others that we'll talk about next week as
well.
So, we'll discuss learning facts from
collections of text via Bayesian networks
and hidden Markov models returning once
more to supervised learning in a different
form, not just classification.
And then, ask what use such rules and
facts are if in fact one doesn't believe
John Sterling and one believes that one
can reason using rules and facts to
connect the dots and make sense of the
world just the way we put two and two
together.
We'll talk about logical, as well as
probabilistic reasoning, reasoning under
uncertainty, and most importantly, the
semantic web, where attempts have been
made to put all these reasoning techniques
together in the context of data on the
web, extracting facts and reasoning about
facts as being a higher order capability
that today the web doesn't have. But,
might well do so in the very near future.
So, see you next week.