Imagen de Portada

Understanding Learning Dynamics Through Structured Representations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Nikooroo, Saleh, Engel, Thomas
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Cross-Model Semantics in Representation Learning
por: Nikooroo, Saleh, et al.
Publicado: (2025)

Structured Transformations for Stable and Interpretable Neural Computation
por: Nikooroo, Saleh, et al.
Publicado: (2025)

Belief Graphs with Reasoning Zones: Structure, Dynamics, and Epistemic Activation
por: Nikooroo, Saleh, et al.
Publicado: (2025)

Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria
por: Nikooroo, Saleh, et al.
Publicado: (2025)

Toward a Graph-Theoretic Model of Belief: Confidence, Credibility, and Structural Coherence
por: Nikooroo, Saleh
Publicado: (2025)

Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
por: Ren, Ruifeng, et al.
Publicado: (2023)

Understanding the Staged Dynamics of Transformers in Learning Latent Structure
por: Saha, Rohan, et al.
Publicado: (2025)

Structure-Aware Masking for Protein Representation Learning
por: Walton, Thomas, et al.
Publicado: (2026)

Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning
por: Chemnitz, Dennis, et al.
Publicado: (2024)

Understanding Lookahead Dynamics Through Laplace Transform
por: Sanyal, Aniket, et al.
Publicado: (2025)

Attention-Guided Masked Autoencoders For Learning Image Representations
por: Sick, Leon, et al.
Publicado: (2024)

Learning to Perceive the World Through Control: Empowerment-Based Representation Learning
por: Bastankhah, Mahsa, et al.
Publicado: (2026)

Statistical Properties of the log-cosh Loss Function Used in Machine Learning
por: Saleh, Resve A., et al.
Publicado: (2022)

Advancing Eurasia Fire Understanding Through Machine Learning Techniques
por: Kriuk, Boris
Publicado: (2025)

The Alchemy of Thought: Understanding In-Context Learning Through Supervised Classification
por: Narnoli, Harshita, et al.
Publicado: (2026)

DroughtSet: Understanding Drought Through Spatial-Temporal Learning
por: Tan, Xuwei, et al.
Publicado: (2024)

Towards Understanding the Benefit of Multitask Representation Learning in Decision Process
por: Lu, Rui, et al.
Publicado: (2025)

What Do GNNs Actually Learn? Towards Understanding their Representations
por: Nikolentzos, Giannis, et al.
Publicado: (2023)

A Survey of Weight Space Learning: Understanding, Representation, and Generation
por: Han, Xiaolong, et al.
Publicado: (2026)

Understanding Deep Learning defenses Against Adversarial Examples Through Visualizations for Dynamic Risk Assessment
por: Echeberria-Barrio, Xabier, et al.
Publicado: (2024)

Enhancing Courier Scheduling in Crowdsourced Last-Mile Delivery through Dynamic Shift Extensions: A Deep Reinforcement Learning Approach
por: Saleh, Zead, et al.
Publicado: (2024)

Constrained Machine Learning Through Hyperspherical Representation
por: Signorelli, Gaetano, et al.
Publicado: (2025)

Dynamical Implicit Neural Representations
por: Park, Yesom, et al.
Publicado: (2025)

DynamicRTL: RTL Representation Learning for Dynamic Circuit Behavior
por: Ma, Ruiyang, et al.
Publicado: (2025)

KinForm: Kinetics Informed Feature Optimised Representation Models for Enzyme $k_{cat}$ and $K_{M}$ Prediction
por: Alwer, Saleh, et al.
Publicado: (2025)

Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization
por: Kuang, Yilun, et al.
Publicado: (2026)

Koopman Autoencoders Learn Neural Representation Dynamics
por: Aswani, Nishant Suresh, et al.
Publicado: (2025)

Understanding Structural Representation in Foundation Models for Polymers
por: Park, Nathaniel H., et al.
Publicado: (2025)

Achieving Upper Bound Accuracy of Joint Training in Continual Learning
por: Momeni, Saleh, et al.
Publicado: (2025)

EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
por: Zhong, Haodi, et al.
Publicado: (2025)

Understanding Representation Learnability of Nonlinear Self-Supervised Learning
por: Yang, Ruofeng, et al.
Publicado: (2024)

When Representations Align: Universality in Representation Learning Dynamics
por: van Rossem, Loek, et al.
Publicado: (2024)

Dynamic Scene Understanding from Vision-Language Representations
por: Pruss, Shahaf, et al.
Publicado: (2025)

Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition
por: Aswani, Nishant Suresh, et al.
Publicado: (2024)

Cheeger--Hodge Contrastive Learning for Structurally Robust Graph Representation Learning
por: Zhao, Mengyang, et al.
Publicado: (2026)

Dynamic Time-aware Continual User Representation Learning
por: Choi, Seungyoon, et al.
Publicado: (2025)

Marrying Causal Representation Learning with Dynamical Systems for Science
por: Yao, Dingling, et al.
Publicado: (2024)

Dynamic Graph Representation Learning for Passenger Behavior Prediction
por: Xie, Mingxuan, et al.
Publicado: (2024)

Foundation Model's Embedded Representations May Detect Distribution Shift
por: Vargas, Max, et al.
Publicado: (2023)

RiboSphere: Learning Unified and Efficient Representations of RNA Structures
por: Zhang, Zhou, et al.
Publicado: (2026)