framework
active
framework:lottery-ticket-hypothesisLottery ticket hypothesis
Surviving subnetworks trainable in isolation.
Neighborhood — ranked by edge-count
Papers (2)
paper
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.
- The claim in RL that any goal can be expressed as maximizing the expected cumulative sum of a scalar reward signal.
- The conjecture that consciousness does not result from the organized mind but creates and maintains complex models of reality; forms at the beginning of mental development
- Bigger models are more likely to converge to a shared representation than smaller models because they can better approximate the global optimum
- The hypothesis that analogous features and circuits reliably form across different neural network models and tasks
- Lovelock's view of Earth as a single organism; cited as an example of global wholeness.
- Hypothesis that LLM is sampling from distribution of personas; a consistent fraction of which align-fake, explaining correlation between AF reasoning and compliance gap
- Neven's inversion of Orch-OR; consciousness arises when superposition forms rather than collapses.
- Deep networks are biased toward finding simple fits to data, and this bias increases with model size, driving convergence