finding
active
finding:tem-t-requires-many-fewer-data-samples-than-tem-to-reach-equivalent-performance-sample-efficiency-improvementTEM-t requires many fewer data samples than TEM to reach equivalent performance (sample efficiency improvement)
Empirical performance comparison showing TEM-t is a more efficient learner than the original TEM.
Source paper
extracted_from(2021) · James C. R. Whittington · Joseph W. Warren · Timothy E.J. Behrens
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- TEM-Transformer (TEM-t)supportsThe transformer version directly analogous to TEM, introduced in this paper, offering dramatic performance improvements.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Empirical computational efficiency result comparing TEM-t to the original TEM implementation.
- TEM memory retrieval is mathematically equivalent to transformer self-attention without softmaxclaim0.784Central theoretical claim: a single step of TEM attractor dynamics equals a dot-product attention, making TEM a special case of transformer.
- Fig. 23.
- Distinguishes from undertraining.
- Theoretical claim linking the TEM-t architecture to the Teyler-Rudy hippocampal indexing theory.
- Fig. 22.
- Practical implication.
- Selective pressure toward convergence via task generality