Dontopedia

Mean Absolute Error (MAE)

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-08.)

Mean Absolute Error (MAE) has 8 facts recorded in Dontopedia across 3 references, with 2 live disagreements.

8 facts·5 predicates·3 sources·2 in dispute

Mostly:rdf:type(2), takes arguments(2), computed as(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (8)

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.

importsImports(2)

includesIncludes(2)

assignsAssigns(1)

computesComputes(1)

providesProvides(1)

source-ofSource of(1)

Other facts (7)

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.

7 facts
PredicateValueRef
Rdf:typeMetric[1]
Rdf:typeEvaluation Metric[3]
Takes ArgumentsTrue Labels[2]
Takes ArgumentsPredictions[2]
Computed AsMae[2]
ComputesAbsolute Error Metric[2]
Imported FromSklearn Metrics[3]

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.

typebeam/b80861a1-4d78-42bf-910d-0bb6e355c0ce
ex:Metric
computed-asbeam/aa30ec0a-322c-4ccb-87f1-9529eeaae311
ex:mae
takes-argumentsbeam/aa30ec0a-322c-4ccb-87f1-9529eeaae311
ex:true-labels
takes-argumentsbeam/aa30ec0a-322c-4ccb-87f1-9529eeaae311
ex:predictions
computesbeam/aa30ec0a-322c-4ccb-87f1-9529eeaae311
ex:absolute-error-metric
typebeam/f2678e4a-540e-4faf-adb9-08586dd85d9c
ex:EvaluationMetric
labelbeam/f2678e4a-540e-4faf-adb9-08586dd85d9c
Mean Absolute Error (MAE)
importedFrombeam/f2678e4a-540e-4faf-adb9-08586dd85d9c
ex:sklearn-metrics

References (3)

3 references
  1. ctx:claims/beam/b80861a1-4d78-42bf-910d-0bb6e355c0ce
    • full textbeam-chunk
      text/plain1 KBdoc:beam/b80861a1-4d78-42bf-910d-0bb6e355c0ce
      Show excerpt
      loss = loss_fn(outputs, batch_labels) val_loss += loss.item() val_loss /= len(val_loader) print(f"Epoch [{epoch+1}/{num_epochs}], Val Loss: {val_loss:.4f}") # Early stopping if val_loss < best_v
  2. ctx:claims/beam/aa30ec0a-322c-4ccb-87f1-9529eeaae311
    • full textbeam-chunk
      text/plain1 KBdoc:beam/aa30ec0a-322c-4ccb-87f1-9529eeaae311
      Show excerpt
      # Early stopping if val_loss < best_val_loss: best_val_loss = val_loss counter = 0 else: counter += 1 if counter >= patience: print("Early stopping") break ``` #### 4. Ev
  3. ctx:claims/beam/f2678e4a-540e-4faf-adb9-08586dd85d9c

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.