This paper clarifies several points from a previous publication which missed a constant in Assumption 3 and another aspect of Assumption 4, and then provides examples to show that the assumptions after the clarification has been made are consistent with previously published assumptions.
In this clarification of assumptions in the relationship between the Bayes Decision Rule and the Whitened Cosine Similarity Measure, this paper first clarifies Assumption 3 (which misses a constant) and Assumption 4 (where the whitened pattern vectors represent the whitened means) in the paper ";The Bayes Decision Rule Induced Similarity Measures"; (IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 6, pp. 1086- 1090, June 2007) and then provides examples to show that the assumptions after the clarification are consistent. (Published abstract provided)