On learning to recognize 3-D objects from examples
Shimon Edelman · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1993
Previous results on nonlearnability of visual concepts relied on the assumption that such concepts are represented as sets of pixels. The author uses an approach developed by Haussler (1989) to show that under an alternative, feature-based representation, recognition is probably approximately correct (PAC) learnable from a feasible number of examples in a distribution-free manner.>