| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2026-04-08 | Add BP+penalty control (round 19's #4 critical experiment) | YurenHao0426 | |
| 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 | |||
 |
index : faeval.git | |
| Unnamed repository; edit this file 'description' to name the repository. | Ubuntu |
| summaryrefslogtreecommitdiff |