Neural decompositionality is defined via decision-boundary semantic preservation, and language transformers largely satisfy it under SAVED while vision models often do not.
Title resolution pending
6 Pith papers cite this work, alongside 378 external citations. Polarity classification is still indexing.
6
Pith papers citing it
378
external citations · external index
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 3polarities
background 3representative citing papers
EMP maps importance scores to effective sample size N_eff and prunes the lowest N - N_eff components, with a derived lower bound on retained effective mass and upper bound on loss increase.
Harder classification tasks produce neural representations whose accuracy collapses under binarization and shuffling while easier tasks remain robust, defining task complexity via the performance gap between full-precision and perturbed networks.
DroneScan-YOLO reaches 55.3% mAP@50 and 35.6% mAP@50-95 on VisDrone2019-DET by combining 1280x1280 input, RPA-Block pruning, MSFD stride-4 branch, and SAL-NWD loss, beating YOLOv8s by 16.6 and 12.3 points with only 4.1% more parameters.
Koopman theory plus knowledge distillation yields linearized models from pre-trained nets that outperform standard least-squares Koopman approximations on MNIST and Fashion-MNIST in accuracy and stability.
A concept-based pruning method for DNNs guided by interpretable concepts and system requirements produces smaller, computationally efficient models that maintain effectiveness on image classification tasks.
citing papers explorer
-
On the Decompositionality of Neural Networks
Neural decompositionality is defined via decision-boundary semantic preservation, and language transformers largely satisfy it under SAVED while vision models often do not.
-
Effective Model Pruning: Measure The Redundancy of Model Components
EMP maps importance scores to effective sample size N_eff and prunes the lowest N - N_eff components, with a derived lower bound on retained effective mass and upper bound on loss increase.
-
Task complexity shapes internal representations and robustness in neural networks
Harder classification tasks produce neural representations whose accuracy collapses under binarization and shuffling while easier tasks remain robust, defining task complexity via the performance gap between full-precision and perturbed networks.
-
DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery
DroneScan-YOLO reaches 55.3% mAP@50 and 35.6% mAP@50-95 on VisDrone2019-DET by combining 1280x1280 input, RPA-Block pruning, MSFD stride-4 branch, and SAL-NWD loss, beating YOLOv8s by 16.6 and 12.3 points with only 4.1% more parameters.
-
Extraction of linearized models from pre-trained networks via knowledge distillation
Koopman theory plus knowledge distillation yields linearized models from pre-trained nets that outperform standard least-squares Koopman approximations on MNIST and Fashion-MNIST in accuracy and stability.
-
Engineering Resource-constrained Software Systems with DNN Components: a Concept-based Pruning Approach
A concept-based pruning method for DNNs guided by interpretable concepts and system requirements produces smaller, computationally efficient models that maintain effectiveness on image classification tasks.