{"id":733,"date":"2017-03-12T12:11:01","date_gmt":"2017-03-12T12:11:01","guid":{"rendered":"http:\/\/www.kelp-ml.org\/?page_id=733"},"modified":"2017-03-13T15:36:18","modified_gmt":"2017-03-13T15:36:18","slug":"kernel-combinations","status":"publish","type":"page","link":"http:\/\/www.kelp-ml.org\/?page_id=733","title":{"rendered":"Kernel Combinations"},"content":{"rendered":"

KernelCombination<\/a>s combine different kernels, allowing the possibility to simultaneously exploit different data representations. Details on these kernels can be found in (Shawe-Taylor and Cristianini, 2004).<\/p>\n

\n

Linear Kernel Combination<\/h3>\n

Java class<\/strong>: LinearKernelCombination<\/a><\/p>\n

Source code<\/strong>: LinearKernelCombination.java<\/a><\/p>\n

Maven Project<\/strong>: kelp-core<\/a><\/p>\n

JSON type<\/strong>:\u00a0linearComb<\/p>\n

Description<\/strong>: given a set n<\/em> of kernels \"K_1, \ldots, K_n\", it computes the weighted sum of the kernel similarities:<\/p>\n

\"K(x,y)\sum_{i\leq n}c_iK_i(x,y)\"<\/p>\n

where\u00a0\"c_i\" are the parametrizable weights of the combination.<\/p>\n

Parameters<\/strong>:<\/p>\n