We prove that the Canonical Distortion Measure (CDM) [2, 3] is the optimal distance measure to use for I nearest-neighbour (l-NN) classifi(cid:173) cation, and show that it reduces to squared Euclidean distance in feature space for function classes that can be expressed as linear combinations of a fixed set of features. PAC-like bounds are given on the sample(cid:173) complexity required to learn the CDM. An experiment is presented in which a neural network CDM was learnt for a Japanese OCR environ(cid:173) ment and then used to do I-NN classification.

We prove that the Canonical Distortion Measure (CDM) [2, 3] is the optimal distance measure to use for I nearest-neighbour (l-NN) classification, and show that it reduces to squared Euclidean distance in feature space for function classes that can be expressed as linear combinations of a fixed set of features. PAClike bounds are given on the samplecomplexity required to learn the CDM. An experiment is presented in which a neural network CDM was learnt for a Japanese OCR environment and then used to do INN classification.

We prove that the Canonical Distortion Measure (CDM) [2, 3] is the optimal distance measure to use for I nearest-neighbour (l-NN) classification, and show that it reduces to squared Euclidean distance in feature space for function classes that can be expressed as linear combinations of a fixed set of features. PAClike bounds are given on the samplecomplexity required to learn the CDM. An experiment is presented in which a neural network CDM was learnt for a Japanese OCR environment and then used to do INN classification.

We prove that the Canonical Distortion Measure (CDM) [2, 3] is the optimal distance measure to use for I nearest-neighbour (l-NN) classification, andshow that it reduces to squared Euclidean distance in feature space for function classes that can be expressed as linear combinations of a fixed set of features.