Nowadays, there are a couple of really excellent online lectures to get you started.
The list is too long to include them all. Every one of the major MOOC sites offers not only one but several good Machine Learning classes, so please check
[coursera](https://www.coursera.org/), [edX](https://www.edx.org/),
[Udacity](https://www.udacity.com/) yourself to see which ones are interesting to you.
However, there are a few that stand out, either because they're very popular
or are done by people who are famous for their work in ML. Roughly in order
from easiest to hardest, those are:
* Andrew Ng's [ML-Class at coursera](https://www.coursera.org/course/ml): Focused
on application of techniques. Easy to understand, but mathematically very shallow.
Good for beginners!
* Daphne Koller's [Probabilistic Graphical Models](https://www.coursera.org/course/pgm)
Is a very challenging class, but has a lot of good material that few of the other.