Update 2021JUN20.md

2021JUN20.md

@@ -107,3 +107,6 @@ The low quality coefficients have similar spike-and-slab priors to enforce spars
 
 
 ## Assume low-quality data is rotated (noiser) version of high quality data
+```math
+P(\mathbf{U}|\mathbf{t}, \mathbf{H}^{L}, \mathbf{w}, \beta_1,...\beta_d) \propto P(\mathbf{t}|\mathbf{X}^{L},\mathbf{U}, \mathbf{w})P(\mathbf{U} | \mathbf{w}, \beta_1,...\beta_d)
+```