Reti neurali come approssimatori universali
Sarei curioso di leggere la dimostrazione di questa affermazione:
A two-layer network with linear outputs can uniformly approximate any continuous function on a compact input domain to arbitrary accuracy, provided the network has a sufficiently large number of hidden units.
fatta dal libro di Bishop, Pattern Recognition and Machine Learning.
Qualcuno ha qualche link, per favore?
A two-layer network with linear outputs can uniformly approximate any continuous function on a compact input domain to arbitrary accuracy, provided the network has a sufficiently large number of hidden units.
fatta dal libro di Bishop, Pattern Recognition and Machine Learning.
Qualcuno ha qualche link, per favore?
