method
active
method:backpropagation-of-errorBackpropagation of Error
Primary training method for neural networks; cited as surprisingly effective even to its inventors, illustrating resistance to full reductionist understanding
Neighborhood — ranked by edge-count
Methods (1)
method
- Backpropagationrelated_toThe training method of modern AI systems; each step computes goal-relative error identified with valence
Claims (1)
claim
- Argument that resistance to reductionism no longer distinguishes life from machines
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.
- Standard learning algorithm for deep neural networks that propagates error signals to adjust weights; lacks convergence guarantee for non-linearly separable functions
- Second category of giving false information: role-playing truth-telling but with incorrect information encoded in weights
- The progressive reduction of error (stress) as cells move toward their target positions.
- Geometrical or functional failures where a decision does not fit harmoniously with the whole; each decision point in a fabricated object is likely a mistake.
- Role in optimizing sensory states; unified treatment shows value-learning and perception share error-minimization principle.
- Model outputs influenced by information from training documents not present in context; relevant to synthetic document fine-tuning results
- Feature detecting mentions of backdoors and hidden malicious functionality.
- SAE latents that rise as correction approaches and peak after self-correction begins, complementing OTDs