Verified65% confidenceBenchmarkExact time
In the same reproduction experiment, ResNet-20 achieved a test accuracy of 90.4% and ResNet-56 achieved a test accuracy of 91.7%, with training accuracies of 97.4% and 99.0% respectively.
3
Sources
65%
Confidence
Long-term
Relevance
8/15/2026
First Seen
Sources
深度网络退化问题实验复现：残差连接为何能拯救深层网络
Related Claims
VerifiedIn a reproduction experiment training for 40 epochs on CIFAR-10, plain-56 achieved a training accuracy of 84.0% and plain-20 achieved a training accuracy of 95.1%, even though plain-56's parameter count (853,018) is approximately three times that of plain-20 (269,722).79% similarUnverifiedThe accuracy data in the test has an error margin of approximately ±8–10 percentage points at n=100 sample size (based on a 95% confidence-level binomial confidence interval).77% similarUnverifiedIn the benchmark test, Logistic Regression achieved 86.7% overall accuracy, 100.0% impact recall, and 0.0% cadence false positives.74% similarUnverifiedThe handwritten MLP model can achieve approximately 98.5% accuracy on the full MNIST training set.73% similarUnverifiedOn a test set of 100 tickets, SupportOps-AI had an escalation error rate of 18%, a hallucination rate of 6%, an infinite-loop rate of 3%, and a complete failure/unresolved rate of 4%.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/750221API
curl https://kongchang.com/api/v1/knowledge/claims/750221MCP
get_claim(id=750221)