AI article
Pocket Data Science IV: Tackling Kaggle MNIST on Android with Antigravity CLI
Community description: How we climbed from zero-parameter baselines to Top 47% (Rank #406 / 863) on Kaggle Digit Recognizer using 126k dual-axis augmented subspace SVM on an Android phone CPU.
Dev.to | Sep 27, 2026 | Malcolm Low
Automated excerpt
In this fourth installment, we step into computer vision using the classic Kaggle Digit Recognizer (MNIST) benchmark (42,000 training images, 28,000 test images, 784 grayscale pixels each). Across 10 distinct experiments over 2 days, our submissions climbed from naive random guessing (0. 10139) all the way to 0. 98792 (Rank #406 of 863 teams, Top 47. 05%, beating 457 teams). Empirical Random Guessing (10. 14%): Sampling labels according to the empirical training class distribution matched theoretical expectation for 10 balanced classes (~10%).
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.