Files
Rbm/source
jensandClaude Sonnet 5 af35c0902d Add mnist to the test suite
Single-layer Deep stack (28x28->256), has saved weights and a larger
training batch than the other mnist variants (test run took noticeably
longer). Passes: reconstruction error 0.005 vs. mean-baseline 0.067.
9/12 pass.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016K8Gu7Qejd11JbdiHZqYAs
2026-07-27 15:01:31 +02:00
..
2024-01-22 12:26:03 +01:00
2024-01-22 12:26:03 +01:00
2024-01-22 13:55:51 +01:00
2024-01-22 12:26:03 +01:00
2024-01-22 12:26:03 +01:00
2026-07-27 15:01:31 +02:00
2024-01-22 13:55:51 +01:00
2024-01-22 13:55:51 +01:00
2024-01-22 13:55:51 +01:00
2026-07-26 21:49:32 +02:00
2022-01-18 20:14:56 +00:00
2022-01-17 18:40:50 +00:00