framework
active
framework:tem-transformer-tem-t

TEM-Transformer (TEM-t)

The transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.

Neighborhood — ranked by edge-count

Thinkers (1)

thinker

Methods (6)

method
  • Key modification to transformers proposed in this paper: position encodings generated by a recurrent network trained on action sequences.
  • Modification to transformer restricting keys and values to previous time-steps only, mimicking how an agent accumulates experiences.
  • Key architectural modification restricting queries and keys to position encodings while values depend only on stimuli; extreme version of best-practice insight.
  • Method for stabilising drifting recurrent position encodings by querying stored landmark memories to correct path-integrated position.
  • Training paradigm requiring prediction of upcoming sensory observations during spatial navigation across multiple environments sharing the same structure.
  • Implementation detail weighting softmax by log(n_memories) to prevent down-weighting of attention values as memory set grows.

Concepts (1)

concept
  • Self-attention
    implements
    A form of key-query attention within a single input sequence; core to Transformers.

Frameworks (5)

framework
  • Neuroscience model of hippocampal formation that the paper shows is mathematically equivalent to a transformer with recurrent position encodings.
  • Biologically plausible two-pool architecture from Krotov & Hopfield (2020) splitting self-attention into feature and memory neuron populations; used to interpret TEM-t place cells.
  • Theory that hippocampus provides an index binding together cortical patterns across different brain regions; TEM-t is shown to instantiate this.
  • Extension of TEM-t to handle conjunctions of more than two brain regions with linear (not exponential) scaling in hippocampal neuron count.
  • Core machine learning architecture analyzed in the paper; shown to be mathematically related to TEM.

Findings (2)

finding

Conceptual bridges

2-hop · via this framework's ideas

Where ideas in this framework connect to the rest of the corpus — the same concept, an analogy, or a restatement elsewhere.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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