Image de couverture de livre

Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wetzel, Sebastian J., Patel, Zakaria
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

Closed-Form Interpretation of Neural Network Classifiers with Symbolic Gradients
par: Wetzel, Sebastian Johann
Publié: (2024)

Deriving Equivalent Symbol-Based Decision Models from Feedforward Neural Networks
par: Seidel, Sebastian, et autres
Publié: (2025)

Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
par: Prokopiou, Ioannis, et autres
Publié: (2026)

Symbol Correctness in Deep Neural Networks Containing Symbolic Layers
par: Bembenek, Aaron, et autres
Publié: (2024)

Sparse Interpretable Deep Learning with LIES Networks for Symbolic Regression
par: Montazerin, Mansooreh, et autres
Publié: (2025)

The Latent Space Hypothesis: Toward Universal Medical Representation Learning
par: Patel, Salil
Publié: (2025)

Gradient-Based Program Synthesis with Neurally Interpreted Languages
par: Macfarlane, Matthew V., et autres
Publié: (2026)

Interpretable Neural-Symbolic Concept Reasoning
par: Barbiero, Pietro, et autres
Publié: (2023)

Operator Feature Neural Network for Symbolic Regression
par: Deng, Yusong, et autres
Publié: (2024)

PruneSymNet: A Symbolic Neural Network and Pruning Algorithm for Symbolic Regression
par: Wu, Min, et autres
Publié: (2024)

Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces
par: Geissler, Daniel, et autres
Publié: (2024)

Interpretable Machine Learning in Physics: A Review
par: Wetzel, Sebastian Johann, et autres
Publié: (2025)

Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression
par: Acero, Fernando, et autres
Publié: (2024)

CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
par: Rao, Xuan, et autres
Publié: (2022)

Distilling Symbolic Priors for Concept Learning into Neural Networks
par: Marinescu, Ioana, et autres
Publié: (2024)

Latent Communication in Artificial Neural Networks
par: Moschella, Luca
Publié: (2024)

Learning Interpretable Network Dynamics via Universal Neural Symbolic Regression
par: Hu, Jiao, et autres
Publié: (2024)

Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analytics
par: Santamaria-Valenzuela, Inmaculada, et autres
Publié: (2025)

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
par: Cloud, Alex, et autres
Publié: (2024)

Axiomatization of Gradient Smoothing in Neural Networks
par: Zhou, Linjiang, et autres
Publié: (2024)

Faithful Interpretation for Graph Neural Networks
par: Hu, Lijie, et autres
Publié: (2024)

Emergent Symbol-like Number Variables in Artificial Neural Networks
par: Grant, Satchel, et autres
Publié: (2025)

GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks
par: Sanderson, Jacob, et autres
Publié: (2026)

Interpretable by AI Mother Tongue: Native Symbolic Reasoning in Neural Models
par: Liu, Hung Ming
Publié: (2025)

Gradient Inversion Attack on Graph Neural Networks
par: Sinha, Divya Anand, et autres
Publié: (2024)

GradINN: Gradient Informed Neural Network
par: Aglietti, Filippo, et autres
Publié: (2024)

Gradient-Free Training of Quantized Neural Networks
par: Cohen, Noa, et autres
Publié: (2024)

Vertical Symbolic Regression via Deep Policy Gradient
par: Jiang, Nan, et autres
Publié: (2024)

Interpreting Neural Networks through Mahalanobis Distance
par: Oursland, Alan
Publié: (2024)

Training Neural Networks for Modularity aids Interpretability
par: Golechha, Satvik, et autres
Publié: (2024)

The Interpretable and Effective Graph Neural Additive Networks
par: Bechler-Speicher, Maya, et autres
Publié: (2024)

Interpretable Neural Networks with Random Constructive Algorithm
par: Nan, Jing, et autres
Publié: (2023)

Interpretable Graph Neural Networks for Tabular Data
par: Alkhatib, Amr, et autres
Publié: (2023)

Factor Graph-based Interpretable Neural Networks
par: Li, Yicong, et autres
Publié: (2025)

Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions
par: Mhammedi, Zakaria
Publié: (2024)

Closed-Form Concept Erasure via Double Projections
par: Zhang, Chi, et autres
Publié: (2026)

Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space
par: Stölzle, Maximilian, et autres
Publié: (2024)

Uncertainty Quantification for Gradient-based Explanations in Neural Networks
par: Mulye, Mihir, et autres
Publié: (2024)

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
par: Huang, Haoyu, et autres
Publié: (2026)

A Comprehensive Survey on Self-Interpretable Neural Networks
par: Ji, Yang, et autres
Publié: (2025)