ARTFEED — Contemporary Art Intelligence

CNN Ablation Study Achieves 89.23% Accuracy on CIFAR-10

other · 2026-04-29

An empirical investigation has thoroughly assessed 17 innovative alterations to a convolutional neural network (CNN) using the CIFAR-10 benchmark. The initial model recorded a test accuracy of 79.5%. Increasing the training time consistently enhanced results, whereas various structural changes led to decreased accuracy despite increased architectural diversity. Utilizing the most effective individual setups, a weighted ensemble reached an accuracy of 86.38% with reduced data and 89.23% with the complete dataset. This research emphasizes that straightforward training modifications can yield better outcomes than intricate architectural adjustments.

Key facts

  • 17 progressive modifications evaluated
  • Baseline accuracy: 79.5%
  • Weighted ensemble accuracy: 86.38% (reduced data), 89.23% (full data)
  • Training duration extension improved performance
  • Some structural redesigns reduced accuracy
  • Study focuses on CIFAR-10 benchmark
  • Modifications include training duration, learning-rate scheduling, dropout, pooling, depth, filter arrangement, dense-layer design
  • Goal: identify changes that improve generalization vs. increase complexity without benefit

Entities

Sources