Imagen de Portada

ScoresActivation: A New Activation Function for Model Agnostic Global Explainability by Design

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Covaci, Emanuel, Galis, Fabian, Balan, Radu, Zaharie, Daniela, Onchis, Darian
Formato:	Preprint
Publicado:	2025
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

Refining Filter Global Feature Weighting for Fully-Unsupervised Clustering
por: Galis, Fabian, et al.
Publicado: (2025)

ExDDV: A New Dataset for Explainable Deepfake Detection in Video
por: Hondru, Vlad, et al.
Publicado: (2025)

Sisteme Hibride de Invatare Automata si Aplicatii
por: Hogea, Eduard, et al.
Publicado: (2024)

Global Convergence in Neural ODEs: Impact of Activation Functions
por: Gao, Tianxiang, et al.
Publicado: (2025)

Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models
por: Farsang, Mónika, et al.
Publicado: (2026)

Implementation of an Asymmetric Adjusted Activation Function for Class Imbalance Credit Scoring
por: Li, Xia, et al.
Publicado: (2025)

Mining Generalizable Activation Functions
por: Vitvitskyi, Alex, et al.
Publicado: (2026)

A Method on Searching Better Activation Functions
por: Sun, Haoyuan, et al.
Publicado: (2024)

ANAct: Adaptive Normalization for Activation Functions
por: Peiwen, Yuan, et al.
Publicado: (2022)

Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies
por: Gross, Dennis, et al.
Publicado: (2025)

DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
por: Sankarapu, Vinay Kumar, et al.
Publicado: (2024)

Efficient Search for Customized Activation Functions with Gradient Descent
por: Strack, Lukas, et al.
Publicado: (2024)

Activation Function Design Sustains Plasticity in Continual Learning
por: Lillo, Lute, et al.
Publicado: (2025)

ActivationReasoning: Logical Reasoning in Latent Activation Spaces
por: Helff, Lukas, et al.
Publicado: (2025)

Evaluating Explainability in Machine Learning Predictions through Explainer-Agnostic Metrics
por: Munoz, Cristian, et al.
Publicado: (2023)

A Model-Agnostic Graph Neural Network for Integrating Local and Global Information
por: Zhou, Wenzhuo, et al.
Publicado: (2023)

Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations
por: Joudaki, Amir, et al.
Publicado: (2024)

Physical Consistency of Aurora's Encoder: A Quantitative Study
por: Richards, Benjamin, et al.
Publicado: (2025)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
por: Jiang, Xinyan, et al.
Publicado: (2026)

Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function
por: Abohwo, Jason, et al.
Publicado: (2025)

CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions
por: Zhang, Hong-Kun, et al.
Publicado: (2025)

Developing Training Procedures for Piecewise-linear Spline Activation Functions in Neural Networks
por: Patty, William H
Publicado: (2025)

ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs
por: Zhang, Zhengyan, et al.
Publicado: (2024)

Steering Large Language Model Activations in Sparse Spaces
por: Bayat, Reza, et al.
Publicado: (2025)

CBMAS: Cognitive Behavioral Modeling via Activation Steering
por: Ismail, Ahmed H., et al.
Publicado: (2026)

Toward Improving fNIRS Classification: A Study on Activation Functions in Deep Neural Architectures
por: Adeli, Behtom, et al.
Publicado: (2025)

MetaSymNet: A Tree-like Symbol Network with Adaptive Architecture and Activation Functions
por: Li, Yanjie, et al.
Publicado: (2023)

Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning
por: Mali, Ankur, et al.
Publicado: (2025)

Dynamically Scaled Activation Steering
por: Ferrando, Alex, et al.
Publicado: (2025)

Bridging Explainability and Embeddings: BEE Aware of Spuriousness
por: Păduraru, Cristian Daniel, et al.
Publicado: (2024)

MCD: A Model-Agnostic Counterfactual Search Method For Multi-modal Design Modifications
por: Regenwetter, Lyle, et al.
Publicado: (2023)

Analytical Solution of a Three-layer Network with a Matrix Exponential Activation Function
por: Gai, Kuo, et al.
Publicado: (2024)

SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
por: Omidvar, Amin
Publicado: (2025)

Improving Analog Neural Network Robustness: A Noise-Agnostic Approach with Explainable Regularizations
por: Duque, Alice, et al.
Publicado: (2024)

DARE: Diffusion Language Model Activation Reuse for Efficient Inference
por: Frumkin, Natalia, et al.
Publicado: (2026)

Activation Sparsity Opportunities for Compressing General Large Language Models
por: Dhar, Nobel, et al.
Publicado: (2024)

Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
por: Chanchal, Akchunya, et al.
Publicado: (2025)

GALACTIC: Global and Local Agnostic Counterfactuals for Time-series Clustering
por: Fragkathoulas, Christos, et al.
Publicado: (2026)

Minimizing Collateral Damage in Activation Steering
por: Nguyen, Tam, et al.
Publicado: (2026)

Activation Steering for Chain-of-Thought Compression
por: Azizi, Seyedarmin, et al.
Publicado: (2025)