Skip to main content
. Author manuscript; available in PMC: 2014 Oct 3.
Published in final edited form as: J Mach Learn Res. 2013 Feb;14:499–566.

Figure 16.

Figure 16

Graph of a causal Bayesian network used to trace the TIE* algorithm. The network parameterization is provided in Table 8 in Appendix B. The response variable is T. All variables take values {0,1}. Variables that contain equivalent information about T are highlighted with the same color, for example, variables X1 and X5 provide equivalent information about T; variable X9 and each of the four variable sets {X5,X6}, {X1,X2}, {X1,X6}, {X5,X2} provide equivalent information about T.