Unverified50% confidenceBenchmarkExact time
On the CNN2-with-pruning task, trainable parameters were compressed to 204, with an accuracy of 81.25%.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the MNIST CNN task, MaRN compressed trainable parameters from 107,998 to 1,872 (approximately 57.7x), while maintaining 91.80% accuracy.77% similarUnverifiedDuring training, the held-out FID dropped from 33.7 to 27.0, FD-DINOv2 dropped from 570 to 218, and detector-based object accuracy improved from 65% to 90%.73% similarVerifiedIn 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).72% similarUnverifiedThe 29-million-parameter encoder trained by the researchers achieved a popularity-weighted cross-fold AUC of only 0.486 on 985 statements, indistinguishable from the corpus prior.72% similarUnverifiedIn 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.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/991518API
curl https://kongchang.com/api/v1/knowledge/claims/991518MCP
get_claim(id=991518)