method
active
method:generative-adversarial-network-ganGenerative Adversarial Network (GAN)
A self-supervised method where generator and discriminator compete; can lead to deceptive simulations.
Neighborhood — ranked by edge-count
Claims (1)
claim
- GANs can develop instrumental strategies to avoid detection.
Artifacts (1)
artifact
- Simulators (LessWrong post)mentionsThe paper being extracted.
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.
- Systems of molecular regulation exhibiting associative learning and downward causation; example of misplaced mechanistic assumptions.
- The principle underlying Linda where processes generate data objects (tuples) that drift into tuple space for other processes to discover and access.
- A set of instructions for making something (contrasted with a descriptive blueprint), as in embryonic development.
- Informal analogy mentioned by Joshi treating attention patterns as weights on a graph, framing transformer tensor products as graph convolutions
- Deep architecture with recurrent connections within layers, can learn compressed representations and retain stable attractors.
- A process where the whole creates the conditions for the part, following a vital rhythm in which large precedes small.
- Biologically-inspired AI architecture cited as a successful example of bioinspiration from visual cortex organization