On Distributional Assumptions and Whitened Cosine Similarities June 2008 (vol. 30 no. 6) pp. 1114-1115
Recently, an interpretation of the whitened cosine similarity measure as a Bayes decision rule was proposed (C. Liu, "The Bayes Decision Rule Induced Similarity Measures,'' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 6, pp. 1086-1090, June 2007. This communication makes the observation that some of the distributional assumptions made to derive this measure are very restrictive and, considered simultaneously, even inconsistent. [1] C. Liu, “The Bayes Decision Rule Induced Similarity Measures,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 6, pp. 1086-1090, June 2007.
Index Terms:
Statistical, Classifier design and evaluation
Citation:
Marco Loog, "On Distributional Assumptions and Whitened Cosine Similarities," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 6, pp. 1114-1115, June 2008, doi:10.1109/TPAMI.2007.70838 Usage of this product signifies your acceptance of the Terms of Use. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||