Each element in the weight matrix $\mathbf{W}$ is given the following prior distribution:
$w_{i,\ell }={\gamma }_{i,\ell }^w{\mathrm{TN}}_{[-a_w,a_w]}(0,{\sigma }_{w,0}^2)+(1-{\gamma }_{i,\ell }^w){\mathrm{TN}}_{[-a_w,a_w]}(0,{\sigma }_{w,1}^2)$, for   ${\gamma }_{i,\ell }^w\sim \mathrm{Bernoulli}({\pi }_w)$,
where ${\sigma }_{w,0}^2={(1,000)}^2$, ${\sigma }_{w,1}^2=$ 0.001, $a_w=$ 0.20, and ${\pi }_w=$ 0.20.
Each element in the weight matrix $\mathbf{U}$ is given the following prior distribution:
$u_{i,r}={\gamma }_{i,r}^u{\mathrm{TN}}_{[-a_u,a_u]}(0,{\sigma }_{u,0}^2)+(1-{\gamma }_{i,r}^u){\mathrm{TN}}_{[-a_u,a_u]}(0,{\sigma }_{u,1}^2)$, for   ${\gamma }_{i,r}^u\sim \mathrm{Bernoulli}({\pi }_u)$,
where ${\sigma }_{u,0}^2={(1,000)}^2$, ${\sigma }_{u,1}^2=$ 0.0005, $a_u=$ 0.20, and ${\pi }_u=$ 0.025.
Each element in the weight matrix ${\mathbf{V}}_1$ is given the following prior distribution:
$v_{1,k,i}={\gamma }_{1,k,i}^v\mathrm{Gau}(0,{\sigma }_{v_1,0}^2)+(1-{\gamma }_{1,k,i}^v)\mathrm{Gau}(0,{\sigma }_{v_1,1}^2)$, for   ${\gamma }_{1,k,i}\sim \mathrm{Bernoulli}({\pi }_{v_1})$,
where ${\sigma }_{v_1,0}^2=10,{\sigma }_{v_1,1}^2=$ 0.01, and ${\pi }_{v_1}=$ 0.50.
Each element in the weight matrix ${\mathbf{V}}_2$ is given the following prior distribution:
$v_{2,k,i}={\gamma }_{2,k,i}^v\mathrm{Gau}(0,{\sigma }_{v_2,0}^2)+(1-{\gamma }_{2,k,i}^v)\mathrm{Gau}(0,{\sigma }_{v_2,1}^2)$, for   ${\gamma }_{2,k,i}\sim \mathrm{Bernoulli}({\pi }_{v_2})$,
where ${\sigma }_{v_2,0}^2=$ 0.5, ${\sigma }_{v_2,1}^2=$ 0.05, and ${\pi }_{v_2}=$ 0.25.
Finally, $\mathit{\alpha }\sim \mathrm{Gau}(0,{\sigma }_{\alpha }^2\mathbf{I})$, where ${\sigma }_{\alpha }^2={(.10)}^2$,    $\mathit{\mu }\sim \mathrm{Gau}(0,{\sigma }_{\mu }^2\mathbf{I})$, where ${\sigma }_{\mu }^2=100$,    $\delta \sim \mathrm{Unif}(0,1)$,
${\sigma }_{ϵ}^2\sim \mathrm{IG}({\alpha }_{ϵ},{\beta }_{ϵ})$, where ${\alpha }_{ϵ}=1$ and ${\beta }_{ϵ}=1$.