A Small MLP Learns Digits 0-9 in Order: Toy Continual Learning Results
BlackHC · x · 2026-09-16
The author had Claude run automated research on a toy continual learning problem: a small MLP learns MNIST digit pairs sequentially (0/1 → 2/3 → ... → 8/9), using only each pair's real training images per stage, then tested on all ten digits to see whether it can learn new digits without forgetting old ones. Results are averaged over 3 seeds with 2 epochs per task initially. The author also shares findings on evaluation, loss scaling, and synthetic replay.
Related event: BlackHC's toy continual learning experiment: PCA replay hits 91.1%(6 posts)→
More from Research
- MIT's xvr aligns 2D X-rays with 3D scans in seconds at sub-millimeter precision — nordicinst · 2026-09-16
- AI researchers predicted 2054 for a Millennium Problem; reality arrived far sooner — ben_j_todd · 2026-09-16
- Paper2Agent turns research papers into interactive AI agents (Nature) — EricTopol · 2026-09-16
- CPAL 2027 heads to Tokyo: small conference on parsimony and learning — YiMaTweets · 2026-09-16
- Discrete Beckmann Transport Models: One-Step Discrete Generators Without a Teacher — rishabh16_ · 2026-09-16
- AI models are becoming appliances: great at one thing, bad at everything else — dbreunig · 2026-09-16