Convolutional Neural Networks

Biologically-inspired AI architecture cited as a successful example of bioinspiration from visual cortex organization

Neighborhood — ranked by edge-count

concept

Bioinspiration
implements
Use of biological principles to guide machine design; the paper calls for systematic rather than ad hoc bioinspiration

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.

Neural Networksconcept0.837
Multilayer Perceptronframework0.799
Deep Learningconcept0.795
Learning hierarchical representations of non-decomposable functions; proposed as formal equivalent to ETI process.
Feature (neural network)concept0.789
Scalar function of the input corresponding to a direction in the vector space of neuron activations; claimed to be the fundamental unit of neural networks
Transformer Neural Networkframework0.787
Core machine learning architecture analyzed in the paper; shown to be mathematically related to TEM.
Neural networks, trained with different objectives on different data and modalities, are converging to a shared statistical model of reality in their representation spaces.quote0.781
The paper's central thesis statement, presented prominently after the abstract
Multi Layer Perceptronframework0.779
Network with hidden layers capable of representing non-linearly separable functions, enabling deep model induction
Early layers of convolutional neural networks converge to oriented Gabor-like filters, shared with biological visual systemsfinding0.772
Evidence that convergence to similar representations occurs in early layers across artificial and biological systems