Title :
Pattern recognition and Valiant´s learning framework
Author :
Saitta, Lorenza ; Bergadano, Francesco
Author_Institution :
Dipartimento di Inf., Torino Univ., Italy
fDate :
2/1/1993 12:00:00 AM
Abstract :
The computational learning approach shows that the concept descriptions acquired from examples are approximately correct with a degree of probability that grows with the size of the training sample. The same problem has also been widely investigated in the field of pattern recognition under a variety of problem settings. Some of the results obtained in both fields are surveyed and compared, and the limits of their applicability are analyzed. Moreover, new and tighter bounds for the growth function of some classes of Boolean formulas are presented
Keywords :
Boolean functions; learning (artificial intelligence); pattern recognition; probability; Boolean formulas; Valiant´s learning framework; computational learning approach; concept descriptions; growth function; pattern recognition; probability; training sample; Error correction; Error probability; Helium; Machine learning; Pattern analysis; Pattern recognition; Terminology;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
