On ImageNet, the 34-layer plain network had higher training error throughout training and higher validation error than the 18-layer plain network, demonstrating optimization degradation with increased depth rather than overfitting.

On ImageNet, the 34-layer plain network had higher training error throughout training and higher validation error than the 18-layer plain network, demonstrating optimization degradation with increased depth rather than overfitting. · CiteArk

Measurement results

0/3 assessed

0 supported0 disputed or conflicting3 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Reported	Latest observation	Evidence judgment
27.94%	—	Not assessed
28.54%	—	Not assessed
3 times nominal schedule	—	Not assessed

On ImageNet, the 34-layer plain network had higher training error throughout training and higher validation error than the 18-layer plain network, demonstrating optimization degradation with increased depth rather than overfitting.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results