Issue No. 09 - September (1999 vol. 21)
<p><b>Abstract</b>—In his comments, Guy Smith discussed three points he believes are either not correct or unclear. These points are: 1) The uniqueness of thermometer coding in the algorithm is not supported in the paper. 2) The BKNN algorithm is not equivalent to the <it>k</it>-nearest neighbor algorithm. 3) The relationship between examplars and classes is not clear. Following is a reply to each of the above three points:</p>
M. R. Kabuka, "Reply to: Comments on 'Design of Supervised Classifiers Using Boolean Neural Networks'," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 21, no. , pp. 957-958, 1999.