Neural-network agents

The artificial agents trained with RL in this study, whose latent dynamics are analyzed for causal emergence.

Neighborhood — ranked by edge-count

paper

concept

Neural Networks
related_to
Artificial agents
associated_with
Synthetic agents (here RL-trained neural networks) whose causal emergence was previously largely unknown; the paper addresses this gap.

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.

non-neural morphogenetic agentsconcept0.807
Agents that exhibit cognition-like behavior without neurons, meeting sentience criteria via electrically active cells.
Neural Network Interventionconcept0.805
The fundamental operation of making in-place changes to model activations, placing the model in a counterfactual state
neural cognitionconcept0.805
Cognition in nervous systems, used as a modelling target
Feature (neural network)concept0.799
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
Neural codeconcept0.784
The model's parameters considered as the actual 'code' implementing its algorithms, as opposed to human-written code.
Neural Cellular Automataframework0.779
Prior framework combining cellular automata with deep learning, extended by this work
Transformer Neural Networkframework0.778
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.quote0.775
The paper's central thesis statement, presented prominently after the abstract