Gradient Descent

Used for updating hidden state expectations; provides dynamical process theory testable against neuronal data

Neighborhood — ranked by edge-count

framework

Differentiable Logic Cellular Automata (DiffLogic CA)
implements
The novel framework introduced in this paper, combining DLGN and NCA for fully differentiable discrete CA learning
Neural Cellular Automata
implements
Prior framework combining cellular automata with deep learning, extended by this work

concept

Continuous Relaxation of Logic Operations
uses
Key technique enabling gradient-based training of discrete logic gates by replacing binary operations with differentiable approximations

method

Gradient method
related_to
Optimization technique that computes weight changes by following the gradient of an error function; contrasted with evolutionary stochastic search.

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.

Gradientsconcept0.882
The property that qualities vary slowly, subtly, gradually across the extent of each living thing; gradients arise as natural responses to changing circumstances and create field-like character that points toward and establishes centers
Gradient Descent on Free Energymethod0.840
Optimization procedure for simultaneously updating action selection and perception; uses step size ζ (default 4).
Gradient-based data attributionmethod0.836
Baseline method against which probe-based ranking is compared; more computationally expensive.
Gradient Descent on Variational Free Energymethod0.834
Process by which neuronal dynamics minimize free energy; produces empirically observable neural phenomena.
Gradients Transformationconcept0.827
A structure-preserving transformation: using gradual change across space to soften and intensify transitions.
Gradient Descent Rotation Optimizationmethod0.819
DAS uses SGD over differentiable parameterizations of orthogonal matrices (via PyTorch) to find optimal distributed alignments.
Gradient conflictconcept0.810
When gradients of different tasks have negative cosine similarity, harming multi-task learning.
Multiple Gradient Descent Algorithm (MGDA)method0.810
Gradient balancing by solving multi-objective optimization for minimum-norm aggregated gradient.