diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 01:33:52 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 01:33:52 -0500 |
| commit | f92ebda7ec2ac155c1a4241b057801c863834e56 (patch) | |
| tree | 7f2595f6ad1c3ad476292b7dad3584fb7acda9ee /results/ep_synthetic/ep_a0.5_L4_s4000.json | |
| parent | 2ca87f2bd4449b1d4ac715d8cf4fb5f20b7afdd8 (diff) | |
Add BP+penalty control (round 19's #4 critical experiment)
Trains end-to-end BP with the same lambda*||f_l(h_l)||^2 penalty used in
the DFA penalty rescue. Tests whether the penalty's depth utilization
loss in penalized DFA is intrinsic to DFA's random-feedback credit
quality (mode 2) or due to penalty-induced capacity regularization.
Decision rule:
BP+pen margin > 25 pp -> mode 2 confirmed (penalty is not the cap)
BP+pen margin < 5 pp -> penalty itself caps depth (capacity loss)
intermediate -> both effects present
Diffstat (limited to 'results/ep_synthetic/ep_a0.5_L4_s4000.json')
0 files changed, 0 insertions, 0 deletions