# Multilayer Perceptron

Features inside a neural network are often carried by groups of neurons acting together, and a circuit drawn as pairwise edges misses the joint effect of suppressing such a group. The new construction treats the network as a structural causal model, uses counterfactual ablations that stay on the neural manifold to progressively suppress a set of neurons, and admits neuron groups into a directed simplicial complex by a statistical relevance test. On two small handcrafted multilayer perceptrons the complexes recover the designed feature pathways, and their 1-skeletons agree with the edges kept by ACDC, EAP and EAP-IG that a weight graph can express.

Features inside a neural network are often carried by groups of neurons acting together, and a circuit drawn as pairwise edges misses the joint effect of suppressing such a group. The new construction treats the network as a structural causal model, uses counterfactual ablations that stay on the neural manifold to progressively suppress a set of neurons, and admits neuron groups into a directed simplicial complex by a statistical relevance test. On two small handcrafted multilayer perceptrons the complexes recover the designed feature pathways, and their 1-skeletons agree with the edges kept by ACDC, EAP and EAP-IG that a weight graph can express.

Using the complementary Shapley-based explainability methods SHAP and νSHAP, this work analyzes neural calibration mappings for the Heston and rough Heston models across multilayer perceptron, highway, and softmax-parametrized highway architectures, finding that short maturities and smile wings consistently dominate parameter inference and that the dominant attribution structure remains qualitatively stable across architectures, and it uses the input redundancy revealed by νSHAP to substantially reduce input dimensionality for rough Heston while matching calibration accuracy relative to the full implied volatility surface.

Using the complementary Shapley-based explainability methods SHAP and νSHAP, this work analyzes neural calibration mappings for the Heston and rough Heston models across multilayer perceptron, highway, and softmax-parametrized highway architectures, finding that short maturities and smile wings consistently dominate parameter inference and that the dominant attribution structure remains qualitatively stable across architectures, and it uses the input redundancy revealed by νSHAP to substantially reduce input dimensionality for rough Heston while matching calibration accuracy relative to the full implied volatility surface.

Using a Multilayer Perceptron Regressor (MLPR) as the base model and a Random Committee hybrid (RC-MLPR), the study predicted the particle Froude number (PFr) in auto-washout drainage systems from five heterogeneous datasets collected from existing literature covering a wide range of hydraulic and sediment conditions, evaluated the models with several performance measures including the agreement index, found that RC-MLPR outperformed other proposed ML models, state-of-the-art ML models, and existing empirical equations, and reported from sensitivity analysis that volumetric sediment concentration (Csed) is the most sensitive variable for PFr prediction by the hybrid RC-MLPR model.

Using a Multilayer Perceptron Regressor (MLPR) as the base model and a Random Committee hybrid (RC-MLPR), the study predicted the particle Froude number (PFr) in auto-washout drainage systems from five heterogeneous datasets collected from existing literature covering a wide range of hydraulic and sediment conditions, evaluated the models with several performance measures including the agreement index, found that RC-MLPR outperformed other proposed ML models, state-of-the-art ML models, and existing empirical equations, and reported from sensitivity analysis that volumetric sediment concentration (Csed) is the most sensitive variable for PFr prediction by the hybrid RC-MLPR model.

Addressing the fact that cooperative perception lets connected vehicles share intermediate neural features while V2X links carry far less than a modern detector produces and existing work reports transmitted bytes without their energy cost, this work decides what to share under a single hard ego-side communication budget: an ensemble of gradient-boosted trees and a multilayer perceptron predicts, from metadata available before any feature is transmitted, how many objects a candidate block would add to what the ego alone detects, and a greedy knapsack allocates the budget across helpers, spatial blocks and numerical fidelity (fp16/int8/int4); on the OPV2V benchmark the allocator reaches 99% of full-fusion AP@0.5 while transmitting 20.0 kB per frame instead of 282.

Addressing the fact that cooperative perception lets connected vehicles share intermediate neural features while V2X links carry far less than a modern detector produces and existing work reports transmitted bytes without their energy cost, this work decides what to share under a single hard ego-side communication budget: an ensemble of gradient-boosted trees and a multilayer perceptron predicts, from metadata available before any feature is transmitted, how many objects a candidate block would add to what the ego alone detects, and a greedy knapsack allocates the budget across helpers, spatial blocks and numerical fidelity (fp16/int8/int4); on the OPV2V benchmark the allocator reaches 99% of full-fusion AP@0.5 while transmitting 20.0 kB per frame instead of 282.