What Organises in Path-Decomposable Neural Network Architectures: On Structural Disposition, Conditional Realisation, and Causal Attribution of Computational Responsibility

Abstract Parametrisations of one neural network architecture can reach nearly the same error yet route their internal computation very differently. Functional error alone is therefore insufficient to show what learning organises. For this reason, we describe multilayer perceptrons (MLPs) and convolutional networks (CNNs) at three levels: their structural disposition, their realisation under a declared condition and their re-realisation after causal intervention. At each level, a symmetry-invariant path measure yields intrinsic observables, together with a layer-conserved flow and a corresponding multiscale flow geometry. Keeping these explanatory layers apart locates each regularity where it holds and provides an intrinsic frame for explaining and interpreting neural networks. We study 2,847 optimiser trajectories from Bayesian AutoML and 149,040 interventions on 324 networks. Learning, formalised as an exact exponential tilt, concentrates the path measure: median effective occupancy falls to 12.9% of its initial value in all 48 MLPs and to 13.0% in 46 of 48 CNNs. The architecture fixes the structural occupancy level, the environment modulates its magnitude and adaptive optimisers drive it down. Within matched MLPs, Adam raises the entropy deficit by 3.323 nats and SGD by only 0.062. Of Adam’s rise, 96.7% follows the validation optimum, so structural and functional time decouple. The geometry records the same reorganisation, as MLPs contract their scale while CNNs internalise flow within boxes. All these findings concern the disposition, which states only what is made available. A conditional realisation provably reweights this structural support at a given state but never extends it. On the MPI3D and Fashion-MNIST benchmarks, reference conditions realise a median of 0.68% and 7.82% of the structural occupancy, respectively, and the activation class shapes which part is realised. Attenuating the realised carriers moves the response more than activation-matched controls in every network, although the activation law decides whether realised or structural carriers matter more. Learning therefore organises a symmetry-faithful field of computational possibility, of which each condition realises a narrower and load-bearing part.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-16
DOI
https://doi.org/10.21203/rs.3.rs-11721788/v1
Primary Topic
Neural Networks and Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

What Organises in Path-Decomposable Neural Network Architectures: On Structural Disposition, Conditional Realisation, and Causal Attribution of Computational Responsibility

Ambarish Moharil, Indika Kumara, Damian Tamburri
1 links
Research Square
Neural Networks and Applications
preprint

What Organises in Path-Decomposable Neural Network Architectures: On Structural Disposition, Conditional Realisation, and Causal Attribution of Computational Responsibility

Ambarish Moharil, Indika Kumara, Damian Tamburri
preprint en

Abstract

Abstract Parametrisations of one neural network architecture can reach nearly the same error yet route their internal computation very differently. Functional error alone is therefore insufficient to show what learning organises. For this reason, we describe multilayer perceptrons (MLPs) and convolutional networks (CNNs) at three levels: their structural disposition, their realisation under a declared condition and their re-realisation after causal intervention. At each level, a symmetry-invariant path measure yields intrinsic observables, together with a layer-conserved flow and a corresponding multiscale flow geometry. Keeping these explanatory layers apart locates each regularity where it holds and provides an intrinsic frame for explaining and interpreting neural networks. We study 2,847 optimiser trajectories from Bayesian AutoML and 149,040 interventions on 324 networks. Learning, formalised as an exact exponential tilt, concentrates the path measure: median effective occupancy falls to 12.9% of its initial value in all 48 MLPs and to 13.0% in 46 of 48 CNNs. The architecture fixes the structural occupancy level, the environment modulates its magnitude and adaptive optimisers drive it down. Within matched MLPs, Adam raises the entropy deficit by 3.323 nats and SGD by only 0.062. Of Adam’s rise, 96.7% follows the validation optimum, so structural and functional time decouple. The geometry records the same reorganisation, as MLPs contract their scale while CNNs internalise flow within boxes. All these findings concern the disposition, which states only what is made available. A conditional realisation provably reweights this structural support at a given state but never extends it. On the MPI3D and Fashion-MNIST benchmarks, reference conditions realise a median of 0.68% and 7.82% of the structural occupancy, respectively, and the activation class shapes which part is realised. Attenuating the realised carriers moves the response more than activation-matched controls in every network, although the activation law decides whether realised or structural carriers matter more. Learning therefore organises a symmetry-faithful field of computational possibility, of which each condition realises a narrower and load-bearing part.

Research Square
Tilburg University (NL), Eindhoven University of Technology (NL)
Neural Networks and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon