Dontopedia
Explore

Mnist Result S3

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

Mnist Result S3 has 8 facts recorded in Dontopedia across 1 reference.

8 facts·8 predicates·1 sources

Mostly:has specific approach(1), implemented in(1), achieved on(1)

Maturity scale raw canonical shape-checked rule-derived certified

Has Specific ApproachhasSpecificApproach

Implemented inimplementedIn

Achieved onachievedOn

Uses MethodusesMethod

Has DurationhasDuration

  • 3 minutes[1]sourceall time · 478

Involves IterationsinvolvesIterations

  • 100[1]sourceall time · 478

Has AccuracyhasAccuracy

  • 96.3[1]sourceall time · 478

Rdf:typerdf:type

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.

achievedOnblah/watt-activation/478
ex:MNIST
hasAccuracyblah/watt-activation/478
96.3
hasDurationblah/watt-activation/478
3 minutes
hasSpecificApproachblah/watt-activation/478
ex:Lohe-approach
implementedInblah/watt-activation/478
ex:Rust
involvesIterationsblah/watt-activation/478
100
typeblah/watt-activation/478
ex:ExperimentalResult
usesMethodblah/watt-activation/478
ex:ManifoldUnit-S³

References (1)

1 references
  1. customctx:discord/blah/watt-activation/478
    • full textwatt-activation-478
      text/plain2 KBdoc:agent/watt-activation-478/0051ed8f-09c6-4572-934e-351b3f5ac139
      Show 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.