U. DE GIOVANNINI

No description

Many works related learning from examples to regularization techniques for inverse prob- lems, emphasizing the strong algorithmic and conceptual analogy of certain learning algo- rithms with regularization algorithms. In particular it is well known that regularization schemes such as Tikhonov regularization can be effectively used in the...

Many works have shown that strong connections relate learning from ex- amples to regularization techniques for ill-posed inverse problems. Nev- ertheless by now there was no formal evidence neither that learning from examples could be seen as an inverse problem nor that theoretical results in learning theory could be independently derived using...