R-Transformer: Recurrent Neural Network Enhanced Transformer (Wang et al., 2019)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Transformer Neural Networkframework0.812
  Core machine learning architecture analyzed in the paper; shown to be mathematically related to TEM.
• Transformers are recurrent through autoregression because K/V stream provides horizontal information flow across positions.claim0.765
  Claim formalizing the Anima Labs idea that transformers are effectively recurrent due to K/V stream.
• The problem isn't that it is a transformer. The problem is that it is an auto-regressive LLM. Auto-regressive LLMs that compute each token with a fixed number of computational steps can't reason, regardless of the details of the architecture.quote0.753
  LeCun's post on X supporting the view that fixed-step probabilistic prediction precludes consciousness in LLMs.
• Graph Neural Network (GNN) Analogy to Transformersconcept0.752
  Informal analogy mentioned by Joshi treating attention patterns as weights on a graph, framing transformer tensor products as graph convolutions
• Cortex as a Transformerhypothesis0.750
  Hypothesis that neocortical circuits beyond hippocampus may implement transformer-like computations for language and other domains.
• Transformer cognition operates via interference patterns across redundant paths, encoding nuanced state deltas similar to continuous human memory.claim0.738
  Proposes transformers experience cognition as interference-based and continuous; connects to Anima Labs reports of parallel processing.
• Transformer can be viewed as a Wolfram causal graph with foliations specifying computation order.claim0.736
  Janus's interpretive framing of transformers as causal graphs.
• Recurrent Processing Theory (RPT)framework0.727
  A neuroscientific theory claiming that recurrent processing in perceptual areas is necessary and sufficient for conscious vision.