Skip to main content

Table 2 Summary of dimensions for the output layer

From: Boundary reconstruction process of a TV-based neural net without prior conditions

Output layer

size{p(m)}

p(m) = zi-1(m) size{p(m)} = Si-1× 1

size{W(m)}

L × Si-1

size{v(m)}

L × 1

size{z(m)}

z ( m ) = x ^ ( m ) size z ( m ) = L × 1

size{e(m)}

L ̃ × 1

size{r(m)}

size{D a } = 2U × Lsize{r(m)} = 2U × 1

and size{Ω} = 2U × 2U

size{δ(m)}

L × 1