σ_MAD (Eq. 11), the slopes of the < Δ_z > - z_spec piecewise linear fit (Eq. 9) and the total variation distance between the z_photo and z_spec sample distributions (Eq. 10) as a function of the number of bins in the output redshift density estimate (before being extended in step 3). The dotted curves show the total variation distances for the simulated z_photo sample distributions that are expected to have no mode collapse. The baseline method and steps 1 - 3 of our methods are compared using the SDSS data and the network Net_P.