Image de couverture de livre

Modular addition without black-boxes: Compressing explanations of MLPs that compute numerical integration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yip, Chun Hei, Agrawal, Rajashree, Chan, Lawrence, Gross, Jason
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Compact Proofs of Model Performance via Mechanistic Interpretability
par: Gross, Jason, et autres
Publié: (2024)

Training MLPs on Graphs without Supervision
par: Wang, Zehong, et autres
Publié: (2024)

SimMLP: Training MLPs on Graphs without Supervision
par: Wang, Zehong, et autres
Publié: (2024)

Constructing Efficient Fact-Storing MLPs for Transformers
par: Dugan, Owen, et autres
Publié: (2025)

Batch and match: black-box variational inference with a score-based divergence
par: Cai, Diana, et autres
Publié: (2024)

Weight-based Decomposition: A Case for Bilinear MLPs
par: Pearce, Michael T., et autres
Publié: (2024)

Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
par: Xu, Alec S., et autres
Publié: (2026)

Channel-Wise MLPs Improve the Generalization of Recurrent Convolutional Networks
par: Breslow, Nathan
Publié: (2025)

Mimetic Initialization of MLPs
par: Trockman, Asher, et autres
Publié: (2026)

From Latent Space to Training Data: Explainable Specialization in Minimal MLPs
par: Alba, Enrique, et autres
Publié: (2026)

Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction
par: Qin, Zongyue, et autres
Publié: (2025)

Diffusion-Assisted Distillation for Self-Supervised Graph Representation Learning with MLPs
par: Ahn, Seong Jin, et autres
Publié: (2025)

Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
par: Wu, Lirong, et autres
Publié: (2024)

Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs
par: Wu, Taiqiang, et autres
Publié: (2023)

Meta-Inverse Physics-Informed Neural Networks for High-Dimensional Ordinary Differential Equations
par: Wei, Zhao, et autres
Publié: (2026)

Saliency strikes back: How filtering out high frequencies improves white-box explanations
par: Muzellec, Sabine, et autres
Publié: (2023)

MDMLP-EIA: Multi-domain Dynamic MLPs with Energy Invariant Attention for Time Series Forecasting
par: Zhang, Hu, et autres
Publié: (2025)

MLPMoE: Zero-Shot Architectural Metamorphosis of Dense LLM MLPs into Static Mixture-of-Experts
par: Novikov, Ivan
Publié: (2025)

Surrogate uncertainty estimation for your time series forecasting black-box: learn when to trust
par: Erlygin, Leonid, et autres
Publié: (2023)

Towards plausibility in time series counterfactual explanations
par: Kostrzewa, Marcin, et autres
Publié: (2026)

On the Compressibility of Quantized Large Language Models
par: Mao, Yu, et autres
Publié: (2024)

Surrogate modeling for interpreting black-box LLMs in medical predictions
par: Han, Changho, et autres
Publié: (2026)

Dual feature-based and example-based explanation methods
par: Konstantinov, Andrei V., et autres
Publié: (2024)

The Alignment Problem from a Deep Learning Perspective
par: Ngo, Richard, et autres
Publié: (2022)

Can persistent homology whiten Transformer-based black-box models? A case study on BERT compression
par: Balderas, Luis, et autres
Publié: (2023)

Towards consistency of rule-based explainer and black box model -- fusion of rule induction and XAI-based feature importance
par: Kozielski, Michał, et autres
Publié: (2024)

Looped ReLU MLPs May Be All You Need as Practical Programmable Computers
par: Liang, Yingyu, et autres
Publié: (2024)

From Black-box to Causal-box: Towards Building More Interpretable Models
par: Hwang, Inwoo, et autres
Publié: (2025)

Actionable and diverse counterfactual explanations incorporating domain knowledge and plausibility constraints
par: Bobek, Szymon, et autres
Publié: (2025)

IMPACTX: improving model performance by appropriately constraining the training with teacher explanations
par: Apicella, Andrea, et autres
Publié: (2025)

Towards a perturbation-based explanation for medical AI as differentiable programs
par: Abe, Takeshi, et autres
Publié: (2025)

HyConEx: Hypernetwork classifier with counterfactual explanations for tabular data
par: Marszałek, Patryk, et autres
Publié: (2025)

COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance
par: Gross, Dennis
Publié: (2026)

COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management
par: Gross, Dennis
Publié: (2026)

Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC
par: Gross, Dennis
Publié: (2026)

Mathematical Models of Computation in Superposition
par: Hänni, Kaarel, et autres
Publié: (2024)

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
par: Yang, Ling, et autres
Publié: (2023)

How can we trust opaque systems? Criteria for robust explanations in XAI
par: Boge, Florian J., et autres
Publié: (2025)

Making deep neural networks right for the right scientific reasons by interacting with their explanations
par: Schramowski, Patrick, et autres
Publié: (2020)

Model Science: getting serious about verification, explanation and control of AI systems
par: Biecek, Przemyslaw, et autres
Publié: (2025)