method
active
method:gradient-descent-rotation-optimizationGradient Descent Rotation Optimization
DAS uses SGD over differentiable parameterizations of orthogonal matrices (via PyTorch) to find optimal distributed alignments.
Neighborhood — ranked by edge-count
Methods (1)
method
- The core method introduced in this paper: finds alignments between high-level causal variables and distributed neural representations via gradient descent.
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.
- Used for updating hidden state expectations; provides dynamical process theory testable against neuronal data
- Process by which neuronal dynamics minimize free energy; produces empirically observable neural phenomena.
- Optimization technique that computes weight changes by following the gradient of an error function; contrasted with evolutionary stochastic search.
- Optimization procedure for simultaneously updating action selection and perception; uses step size ζ (default 4).
- A structure-preserving transformation: using gradual change across space to soften and intensify transitions.
- Gradient balancing by solving multi-objective optimization for minimum-norm aggregated gradient.
- Baseline method against which probe-based ranking is compared; more computationally expensive.
- Gradient that tells a cell its correct position; stress arises from deviation from this gradient.