{"responseHeader":{"status":0,"QTime":4,"params":{"q":"{!q.op=AND}id:\"102871\"","hl":"true","hl.simple.post":"","hl.fragsize":"5000","fq":"!embargo_tdt:[NOW TO *]","hl.fl":"ocr_t","hl.method":"unified","wt":"json","hl.simple.pre":""}},"response":{"numFound":1,"start":0,"docs":[{"file_name_t":"Soller-Automated_Detection.pdf","thumb_s":"/ae/2a/ae2a3659cf2824d56510c1a99dbb6dc497d4dd81.jpg","oldid_t":"compsci 10984","setname_s":"ir_computersa","restricted_i":0,"format_t":"application/pdf","modified_tdt":"2016-05-26T00:00:00Z","file_s":"/1f/ee/1fee1aa8af8e2d85cc77e8c411a856ebe80e4810.pdf","title_t":"Page 114","ocr_t":"99 • tensor product of partial derivatives of logistic function, (11.103) • tensor product of univariate sine functions, rr sin ( 7rxi/2.5) ; i=l 'lrXi /2.5 (11.104) • tensor product with poles at x1 = 5 ± i, x2 = 5 ± i and X3 = ±5 ± i, lxj I < 5, 1 1 1 1 (11.105) and • uniform random data in the interval [ -5, 5]. The five functions were evaluated using equispaced, uniform random, and Gaussian random distributions. As expected, the Gaussian distribution without an appropriate conformal mapping produced ill-conditioned matrices. The equispaced distribution produced well-conditioned matrices. The number of bases were always less than or equal to the number of data points. As the number of bases approached the number of data points, the training data performance measure approached zero and the test data performance measure increased; in these cases, the model overfit the sample data. The squared error performance of the sine basis and the Gaussian basis was similar over the five functions . The sine basis function produced lower condition numbers than the Gaussian basis function in most cases. 11.9.2 Performance on Delirium Data The sine tensor product network was applied to the problem of detecting delirium given the six laboratory data factors. The 25 laboratory values were not directly","id":102871,"created_tdt":"2016-05-26T00:00:00Z","parent_i":102961,"_version_":1642982670140964865}]},"highlighting":{"102871":{"ocr_t":[]}}}