adds test for KFC

[tfjgeorge]

BUGFIX: KFAC for convolutions was scaled by the # of spatial positions but it should not.

actually the former implementation corresponds to what is derived in the KFC paper. However arguably the scaling by 1/S with S the number of spatial positions might not be optimal (see discussion in derivations/kfc.pdf) thus I instead scaled the test by S and reverted back to KFC expressions.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (d7225d9) 94.13% compared to head (ade2a1d) 94.89%.

Additional details and impacted files

@@            Coverage Diff             @@
##           master      #75      +/-   ##
==========================================
+ Coverage   94.13%   94.89%   +0.75%     
==========================================
  Files          31       31              
  Lines        3479     3464      -15     
==========================================
+ Hits         3275     3287      +12     
+ Misses        204      177      -27     

Flag	Coverage Δ
unittests	94.89% <100.00%> (+0.75%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.