Unnamed repository; edit this file 'description' to name the repository. http://git.genenetwork.org/BNW/atom?h=main 2021-02-24T20:36:59+00:00 2021-02-24T20:36:59+00:00 ziejd2 2021-02-24T20:36:59+00:00 urn:sha1:25b843f6bbacb1937bdb960777b73acbece64115 2019-01-28T22:31:54+00:00 ziejd2 2019-01-28T22:31:54+00:00 urn:sha1:bb9d93322abf825368dedaafc2376ef8fdfc1e2f 2018-09-14T04:59:20+00:00 ziejd2 2018-09-14T04:59:20+00:00 urn:sha1:e3f7237ffcb19f19db3b68777b5a94b89e07f66a The main change here is in the parameter learning methods. The parameters that are learned at first (i.e., if there is no evidence) are the distributions that are found directly in the data. I had to create or significantly modify several BNT files for this. If there is evidence, the parameters are learned using a Dirichlet prior. This only required a couple of small changes to the BNW parameter learning files. 2018-04-25T21:43:19+00:00 ziejd2 2018-04-25T21:43:19+00:00 urn:sha1:74b673ba4a706085201a5610b938ff98f08f641d 2018-03-15T04:19:16+00:00 ziejd2 2018-03-15T04:19:16+00:00 urn:sha1:c80226899f5cdd9f11c163817d59445213f5bef0 2017-09-28T20:04:40+00:00 ziejd2 2017-09-28T20:04:40+00:00 urn:sha1:8070dc963753142bb86c4ed698d91fd623ed28e7 This version of BNW should perform the same as the original version. The only difference is that it uses Octave instead of Matlab when running BayesNet Toolbox during parameter learning. I am calling this BNW_1.02. It can be accessed at: compbio.uthsc.edu/BNW_1.02 2017-09-14T20:57:50+00:00 ziejd2 2017-09-14T20:39:41+00:00 urn:sha1:c4f926438dcb8abe805e910399940f79ff643c4b