Issue No. 08 - August (1993 vol. 15)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.236244
<p>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.</p>
learning by examples; image recognition; nonlearnability; visual concepts; Haussler; feature-based representation; image recognition; knowledge representation; learning by example
S. Edelman, "On Learning to Recognize 3-D Objects from Examples," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 15, no. , pp. 833-837, 1993.