Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wetzel, Sebastian J., Patel, Zakaria
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Deriving Equivalent Symbol-Based Decision Models from Feedforward Neural Networks
por: Seidel, Sebastian, et al.
Publicado: (2025)

Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
por: Prokopiou, Ioannis, et al.
Publicado: (2026)

Symbol Correctness in Deep Neural Networks Containing Symbolic Layers
por: Bembenek, Aaron, et al.
Publicado: (2024)

Sparse Interpretable Deep Learning with LIES Networks for Symbolic Regression
por: Montazerin, Mansooreh, et al.
Publicado: (2025)

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

Gradient-Based Program Synthesis with Neurally Interpreted Languages
por: Macfarlane, Matthew V., et al.
Publicado: (2026)

Interpretable Neural-Symbolic Concept Reasoning
por: Barbiero, Pietro, et al.
Publicado: (2023)

Operator Feature Neural Network for Symbolic Regression
por: Deng, Yusong, et al.
Publicado: (2024)

PruneSymNet: A Symbolic Neural Network and Pruning Algorithm for Symbolic Regression
por: Wu, Min, et al.
Publicado: (2024)

Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces
por: Geissler, Daniel, et al.
Publicado: (2024)

Interpretable Machine Learning in Physics: A Review
por: Wetzel, Sebastian Johann, et al.
Publicado: (2025)

CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
por: Rao, Xuan, et al.
Publicado: (2022)

Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression
por: Acero, Fernando, et al.
Publicado: (2024)

Distilling Symbolic Priors for Concept Learning into Neural Networks
por: Marinescu, Ioana, et al.
Publicado: (2024)

Latent Communication in Artificial Neural Networks
por: Moschella, Luca
Publicado: (2024)

Learning Interpretable Network Dynamics via Universal Neural Symbolic Regression
por: Hu, Jiao, et al.
Publicado: (2024)

Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analytics
por: Santamaria-Valenzuela, Inmaculada, et al.
Publicado: (2025)

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
por: Cloud, Alex, et al.
Publicado: (2024)

Axiomatization of Gradient Smoothing in Neural Networks
por: Zhou, Linjiang, et al.
Publicado: (2024)

Faithful Interpretation for Graph Neural Networks
por: Hu, Lijie, et al.
Publicado: (2024)

Emergent Symbol-like Number Variables in Artificial Neural Networks
por: Grant, Satchel, et al.
Publicado: (2025)

GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks
por: Sanderson, Jacob, et al.
Publicado: (2026)

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

Gradient Inversion Attack on Graph Neural Networks
por: Sinha, Divya Anand, et al.
Publicado: (2024)

GradINN: Gradient Informed Neural Network
por: Aglietti, Filippo, et al.
Publicado: (2024)

Gradient-Free Training of Quantized Neural Networks
por: Cohen, Noa, et al.
Publicado: (2024)

Vertical Symbolic Regression via Deep Policy Gradient
por: Jiang, Nan, et al.
Publicado: (2024)

Interpreting Neural Networks through Mahalanobis Distance
por: Oursland, Alan
Publicado: (2024)

Training Neural Networks for Modularity aids Interpretability
por: Golechha, Satvik, et al.
Publicado: (2024)

The Interpretable and Effective Graph Neural Additive Networks
por: Bechler-Speicher, Maya, et al.
Publicado: (2024)

Interpretable Neural Networks with Random Constructive Algorithm
por: Nan, Jing, et al.
Publicado: (2023)

Interpretable Graph Neural Networks for Tabular Data
por: Alkhatib, Amr, et al.
Publicado: (2023)

Factor Graph-based Interpretable Neural Networks
por: Li, Yicong, et al.
Publicado: (2025)

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

Closed-Form Concept Erasure via Double Projections
por: Zhang, Chi, et al.
Publicado: (2026)

Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space
por: Stölzle, Maximilian, et al.
Publicado: (2024)

Uncertainty Quantification for Gradient-based Explanations in Neural Networks
por: Mulye, Mihir, et al.
Publicado: (2024)

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
por: Huang, Haoyu, et al.
Publicado: (2026)

A Comprehensive Survey on Self-Interpretable Neural Networks
por: Ji, Yang, et al.
Publicado: (2025)