method
active
method:back-propagation

Back-propagation

Standard learning algorithm for deep neural networks that propagates error signals to adjust weights; lacks convergence guarantee for non-linearly separable functions

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Deep Learning
    implements
    Learning hierarchical representations of non-decomposable functions; proposed as formal equivalent to ETI process.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Backpropagationmethod0.807
    The training method of modern AI systems; each step computes goal-relative error identified with valence
  • Intervention Propagationconcept0.777
    Property that additive modifications to activations affect all downstream computations, enabling tractable behavioral control
  • Belief Propagationmethod0.770
    Inference mechanism underlying active inference; updates posterior beliefs via gradient descent on free energy.
  • Backpropagation of Errormethod0.764
    Primary training method for neural networks; cited as surprisingly effective even to its inventors, illustrating resistance to full reductionist understanding
  • Backplaneconcept0.732
    Core meta-construct and stable component that manages application lifecycle, initialization, and provides standard interfaces for system development.
  • Belief Propagation Algorithmmethod0.730
    Message passing algorithm based on Bethe approximation.
  • BACKPLANE (2)framework0.729
  • Backtracking Latentsconcept0.723
    SAE latents that rise as correction approaches and peak after self-correction begins, complementing OTDs