all tags

catastrophic-forgetting

20 notes carry this tag — 9 claims, 4 observations, 2 questions, 5 captures. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• What genuinely connects claim-brooks-1991-does-not-cite-dreyfus and claim-david-brachet-2011-citing-papers-contain-zero-ml-work: both are the vault's argument-from-silence method testing whether a cross-field name-echo hides real lineage — not the same mechanism, but the same higher-order pattern the vault already calls the jingle fallacy
  capture promoted 2026-08-15 · argument-from-silence, negative-citation, jingle-fallacy, brooks, dreyfus
• The vault's Brooks/Dreyfus and David-Brachet-citing-papers negative-citation findings are both argument-from-silence instances, but only the Brooks/Dreyfus pair is tagged and MOC-indexed as such
  observation seedling Tier 1 2026-08-15 · argument-from-silence, negative-citation, brooks, dreyfus, david-brachet
• The Brooks/Dreyfus and David-Brachet/catastrophic-forgetting bridges share a method but not a mechanism — one silence is a documented redaction, the other is (so far) undocumented non-contact
  observation seedling Tier 1 2026-08-15 · argument-from-silence, negative-citation, brooks, dreyfus, catastrophic-forgetting
• Brooks's and Dreyfus's identically-titled 'Intelligence without representation' papers are an untagged jingle-fallacy instance, alongside the vault's other named one (organizational vs. catastrophic forgetting)
  observation seedling Tier 1 2026-08-15 · jingle-fallacy, argument-from-silence, negative-citation, brooks, dreyfus
• Verify the absence of citation lineage between ML catastrophic-forgetting research and organizational-forgetting research via a proper bibliometric check
  capture promoted 2026-08-12 · catastrophic-forgetting, organizational-forgetting, citation-analysis, bibliometrics, cross-domain-bridge
• The 60 papers citing David & Brachet (2011), per Semantic Scholar, contain no ML or connectionist work
  claim seedling Tier 1 2026-08-12 · catastrophic-forgetting, organizational-forgetting, citation-analysis, bibliometrics, cross-domain-bridge
• David & Brachet (2011)'s complete reference list contains no citation to the ML catastrophic-forgetting literature
  claim seedling Tier 1 2026-08-12 · catastrophic-forgetting, organizational-forgetting, citation-analysis, bibliometrics, cross-domain-bridge
• Semantic Scholar's Graph API elides publisher-controlled reference lists for McCloskey & Cohen (1989) and French (1999), blocking a direct citation-graph check against organizational-forgetting research
  claim seedling Tier 1 2026-08-12 · catastrophic-forgetting, organizational-forgetting, citation-analysis, bibliometrics, source-verification
• Bipartite hop: does catastrophic-forgetting structure-dependence connect to organizational-forgetting's two unrelated traditions?
  capture promoted 2026-08-11 · catastrophic-forgetting, organizational-forgetting, continual-learning, false-bridge, cross-domain-bridge
• No citation or literature lineage connects ML's catastrophic-forgetting research to either organizational-forgetting tradition
  claim seedling Tier 1 2026-08-11 · catastrophic-forgetting, organizational-forgetting, continual-learning, false-bridge, cross-domain-bridge
• David & Brachet (2011) decompose organizational forgetting into a continuous skill-decay channel and a discrete turnover-loss channel
  claim seedling Tier 1 2026-08-11 · organizational-forgetting, learning-curve, catastrophic-forgetting, cross-domain-bridge, economics
• Catastrophic-forgetting and organizational-forgetting research independently converged on the same corrective move against the jingle fallacy
  observation seedling Tier 1 2026-08-11 · catastrophic-forgetting, organizational-forgetting, jingle-fallacy, false-bridge, cross-domain-bridge
• Verify the absence of citation lineage between ML catastrophic-forgetting research and organizational-forgetting research via a proper bibliometric check
  question open 2026-08-11 · catastrophic-forgetting, organizational-forgetting, citation-analysis, source-verification
• Catastrophic forgetting is a structure-dependent regime, not a universal property of neural networks
  claim budding Tier 1 2026-07-18 · catastrophic-forgetting, continual-learning, connectionism, forgetting-curve, representational-overlap
• Kline's MNIST drop-8 protocol is a single-task representational drift, not a disjoint sequential-task switch
  claim seedling Tier 1 2026-07-18 · catastrophic-forgetting, continual-learning, forgetting-curve, mnist, neuro-AI-parallel
• Whether a network forgets catastrophically or gracefully is governed by representational overlap, not by an intrinsic property of backpropagation
  claim seedling Tier 1 2026-07-18 · catastrophic-forgetting, representational-overlap, distributed-representations, sparse-coding, continual-learning
• Is 'catastrophic vs. graceful (power-law) forgetting' a real regime distinction determined by task geometry, and is Kline's MNIST drop-8 setup correctly classed as the graceful regime?
  capture promoted 2026-07-13 · catastrophic-forgetting, continual-learning, forgetting-curve, power-law, neuro-AI-parallel
• A neural network can forget along a graceful, human-like power-law curve — not only catastrophically — when feature overlap preserves the trace
  claim seedling Tier 1 2026-07-12 · catastrophic-forgetting, continual-learning, forgetting-curve, memory, neuro-AI-parallel
• Is 'catastrophic vs. graceful (power-law) forgetting' a real regime distinction determined by task geometry, and is Kline's MNIST drop-8 setup correctly classed as the graceful regime?
  question answered 2026-07-12 · catastrophic-forgetting, continual-learning, forgetting-curve, neuro-AI-parallel, verification
• Neural networks can forget along a human-like power-law curve — and the 1885 spacing effect re-emerges inside them
  capture promoted Tier 1 2026-07-11 · catastrophic-forgetting, continual-learning, forgetting-curve, spaced-repetition, cognitive-science