With Gaussian initialization scale σ_g=12 in the 2D image task, jointly optimizing a_j and b_j with the MLP using Adam does not improve performance relative to leaving the mapping fixed. · CiteArk
Not assessedPlan blockedFindingjoint-feature-no-gain-12
With Gaussian initialization scale σ_g=12 in the 2D image task, jointly optimizing a_j and b_j with the MLP using Adam does not improve performance relative to leaving the mapping fixed.
Source: paper:§A.3 p. 13; Figure 8(a,b)
Reported and observed measurements
No structured measurement is attached to this Claim.
Assessments (0)
No immutable Assessment has been published for this Claim yet.
