Papers › Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods

Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods

24 Jan 2020arXiv:2001.08856archive 2025-07-28

Yahia Assiri

Convolutional neural networks have been achieving the best possible accuracies in many visual pattern classification problems. However, due to the model capacity required to capture such representations, they are often oversensitive to overfitting and therefore require proper regularization to generalize well. In this paper, we present a combination of regularization techniques which work together to get better performance, we built plain CNNs, and then we used data augmentation, dropout and customized early stopping function, we tested and evaluated these techniques by applying models on five famous datasets, MNIST, CIFAR10, CIFAR100, SVHN, STL10, and we achieved three state-of-the-art-of (MNIST, SVHN, STL10) and very high-Accuracy on the other two datasets.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

junaidaliop/MNIST-SOPCNN mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationImage ClassificationStochastic Optimization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods Percentage correct 94.29 #160 of 265 Archive leaderboard report
Image Classification CIFAR-100 SOPCNN PARAMS 4,252,298 #164 of 211 Archive leaderboard report
Image Classification CIFAR-100 SOPCNN Percentage correct 72.96 #164 of 211 Archive leaderboard report
Image Classification MNIST SOPCNN (Only a single Model) Accuracy 99.83 #4 of 81 Archive leaderboard report
Image Classification MNIST SOPCNN (Only a single Model) Percentage error 0.17 #4 of 81 Archive leaderboard report
Image Classification MNIST SOPCNN (Only a single Model) Trainable Parameters 1400000 #4 of 81 Archive leaderboard report
Image Classification STL-10 SOPCNN Percentage correct 88.08 #43 of 117 Archive leaderboard report
Image Classification SVHN SOPCNN Percentage error 1.50 #10 of 62 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

DropoutEarly StoppingSGD

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections