The Learning Problem and Regularization
Tomaso Poggio


We introduce the problem of learning from sparse examples. We introduce key terms and concepts such as loss functions, empirical risk, true risk, generalization error, hypothesis spaces, approximation error and sample error. We introduce two key requirements on learning algorithms: stability and consistency. We then describe Tikhonov regularization -- which in our course is the algorithm with the magic.


Slides for this lecture: PDF

Suggested Reading