digraph ImageClassificationGraph {
        ///////// The forward part /////////
        FeedX [label="Feed", color=blue, shape=box];
        FeedY [label="Feed", color=blue, shape=box];
        FC [label="FC", color=blue, shape=box];
        MSE [label="MSE", color=blue, shape=box];

        x [label="x", color=blue, shape=oval];
        l [label="l", color=blue, shape=oval];
        y [label="y", color=blue, shape=oval];
        W [label="W", color=blue, shape=doublecircle];
        b [label="b", color=blue, shape=doublecircle];
        cost [label="cost", color=blue, shape=oval];

        FeedX -> x -> FC -> y -> MSE -> cost [color=blue];
        FeedY -> l -> FC [color=blue];
        W -> FC [color=blue];
        b -> FC [color=blue];
        l -> MSE [color=blue];

        ////////// The backward part /////////
        MSE_Grad [label="MSE_grad", color=red, shape=box];
        FC_Grad [label="FC_grad", color=red, shape=box];

        d_cost [label="d cost", color=red, shape=oval];
        d_y [label="d y", color=red, shape=oval];
        d_b [label="d b", color=red, shape=oval];
        d_W [label="d W", color=red, shape=oval];

        cost -> MSE_Grad [color=red];
        d_cost -> MSE_Grad [color=red];
        x -> MSE_Grad [color=red];
        l -> MSE_Grad [color=red];
        y -> MSE_Grad -> d_y [color=red];

        x -> FC_Grad [color=red];
        y -> FC_Grad [color=red];
        d_y -> FC_Grad [color=red];
        W -> FC_Grad -> d_W [color=red];
        b -> FC_Grad -> d_b [color=red];

        ////////// The optimizaiton part //////////

        OPT_W [label="SGD", color=green, shape=box];
        OPT_b [label="SGD", color=green, shape=box];

        d_W -> OPT_W -> W [color=green];
        d_b -> OPT_b -> b [color=green];

        ////////// Groupings //////////

        subgraph clusterMSE {
                style=invis;
                MSE;
                MSE_Grad;
        }

        subgraph clusterFC {
                style=invis;
                FC;
                FC_Grad;
        }
}