Agnostic learning of general geometric patterns and multi-instance learning in R/sup d/
Stephen Scott · 2005
The concept class of geometric patterns has been heavily studied and has applications in pattern recognition. Pr evious work on this concept class has been restricted to one or two dimensions or to finite and discretized domains. We present an algorithm to learn a very flexible generalization of previously studied geometric patterns in any constantdimensional real space, making its potential applicabilit y to pattern matching very high since it can operate on any data representable as a constant-dimensional array of values. To our knowledge, these classes of patterns are more complex than any class of geometric patterns previously studied. We also give variations of our algorithms to learn the union of constant-dimensional geometric objects from multiple-instance examples.