framework
active
framework:transformer-neural-networkTransformer Neural Network
Core machine learning architecture analyzed in the paper; shown to be mathematically related to TEM.
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- TEM-Transformer (TEM-t)extendsThe 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.
- Prior work on recurrently generated position encodings; cited as precedent for TEM-t's recurrent position encoding method.
- Informal analogy mentioned by Joshi treating attention patterns as weights on a graph, framing transformer tensor products as graph convolutions
- Biologically-inspired AI architecture cited as a successful example of bioinspiration from visual cortex organization
- The artificial agents trained with RL in this study, whose latent dynamics are analyzed for causal emergence.
- Scalar function of the input corresponding to a direction in the vector space of neuron activations; claimed to be the fundamental unit of neural networks
- Hypothesis that neocortical circuits beyond hippocampus may implement transformer-like computations for language and other domains.
- The field aimed at understanding what neural networks have learned; characterized as pre-paradigmatic in this paper