MNIST Experiment with ManifoldUnit S³
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
MNIST Experiment with ManifoldUnit S³ has 3 facts recorded in Dontopedia across 1 reference.
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (1)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
precedesPrecedes(1)
- Width Depth Ablation Eval
ex:width-depth-ablation-eval
Other facts (2)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Rdf:type | Machine Learning Experiment | [1] |
| Involves Method | Manifold Unit S³ | [1] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (1)
ctx:discord/blah/watt-activation/478- full textwatt-activation-478text/plain2 KB
doc:agent/watt-activation-478/0051ed8f-09c6-4572-934e-351b3f5ac139Show excerpt
[2026-03-21 22:14] xenonfun: ``` ⏺ 96.3% accuracy on MNIST with ManifoldUnit S³ — 100 iterations, 3 minutes. That's essentially matching Python's CNN result (96.2%) with no convolutions at all, just oscillator dynamics on the sphere. ┌…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.