[GitHub] madlib pull request #272: MLP: Add momentum and nesterov to gradient updates...

[njayaram2]

Github user njayaram2 commented on a diff in the pull request:

    https://github.com/apache/madlib/pull/272#discussion_r191533727
  
    --- Diff: src/modules/convex/type/model.hpp ---
    @@ -126,45 +129,96 @@ struct MLPModel {
             for (k = 0; k < N; k ++) {
                 size += static_cast<uint32_t>((n[k] + 1) * (n[k+1]));
             }
    +        //TODO conditionally assign size based on momentum
    --- End diff --
    
    Is this TODO still valid?


---