Fast Fourier Transform-Based Method

Algorithm mentioned alongside Monte Carlo for computing pi, illustrating solution diversity.

Neighborhood — ranked by edge-count

paper

framework

Supervised Learning
associated_with
Learning through physical changes in mechanical networks, as an example of learning outside neural systems.

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.

Gradient methodmethod0.726
Optimization technique that computes weight changes by following the gradient of an error function; contrasted with evolutionary stochastic search.
Fourier featuresconcept0.724
Features identified in Llama-3.1-8B that compute sums using periods respecting base-10 addition (2, 5, 10) rather than concept-specific periods
Forward Algorithmmethod0.715
Used to update pain beliefs online from observations of happiness
Fourier Features for Numerical Computationconcept0.713
Fourier analysis of neural activationsmethod0.710
Method used to identify the periodic features and their periods in Llama-3.1-8B's MLP neurons
To transform a function (in time or in space), apply the transform point-wise to the output, and apply the inverse transform point-wise to the input.claim0.707
General principle for transforming functions that enables spatial transformation of GUIs without reimplementation; connects to Pan's hyperfilters.
computer-based wind tunnel simulationmethod0.703
Simulating wind flow to give immediate feedback on shape, as in the locomotive nose example, enabling iterative adaptation.
Finite Element Analysismethod0.702
Engineering simulation used from the earliest stage to develop the syncopated structural grid for large buildings.