framework
active
framework:gated-recurrent-unit-gruGated Recurrent Unit (GRU)
Recurrent neural network architecture used as the primary model type in numeric task experiments.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Model Alignment Searchmentions
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.
- Multimodal fusion technique combining language and vision representations via learnable gating parameters.
- Portion of a pattern that produces the frieze via translation only
- GRU behavior can be compressed to as few as 4 dimensions using DAS and MAS with comparable IIAsfinding0.704Shows that behaviorally relevant information is low-dimensional; contrasted with model stitching achieving near-perfect IIA at rank 2.
- GRUs trained on the Arithmetic task use different types of numeric representations than incremental counting modelshypothesis0.704Interpretive hypothesis supported by the lower IIA between Count and Cumu Val variables even in the restricted value range.
- The key novel property of DiffLogic CA — logic gate networks that are recurrent both spatially and temporally
- Systems of molecular regulation exhibiting associative learning and downward causation; example of misplaced mechanistic assumptions.
- Claim formalizing the Anima Labs idea that transformers are effectively recurrent due to K/V stream.
- Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.