RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @david_picard: "an optimal parenthesis problem"? I now understand why the first differentiation engines were written in lisp...🤪
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
"an optimal parenthesis problem"? I now understand why the first differentiation engines were written in lisp...🤪
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @BharathMax: Fantastic and Spectacular, really is!
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
Fantastic and Spectacular, really is!
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
RT @gabrielpeyre: The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and back…
The optimal computation of gradients for the composition of functions is an optimal parenthesis problem. Forward and backward (backpropagation) are two extreme cases. Backward is optimal for scalar-valued functions. https://t.co/UVMi13yUHm https://t.co/vP
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
@vit_tucek @gabrielpeyre Jacobian accumulation is NP-complete https://t.co/LkNzQyxZ22
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
@Mathologer @3blue1brown
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…
RT @gabrielpeyre: Optimal computation of gradients is equivalent to optimal parenthesis problem. It is NP hard. Forward and backward (back…